< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3063 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')



Text #0

Max Range: 11.3338. Min Range: -11.3338

Max Act: 11.3338. Min Act: -0.1700

Data Index: 1644914 (Open Web Text)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 11.3338. Min Range: -11.3338

Max Act: 11.1463. Min Act: -0.1700

Data Index: 6181330 (Open Web Text)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 11.3338. Min Range: -11.3338

Max Act: 11.0213. Min Act: -0.1700

Data Index: 2490642 (Open Web Text)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 11.3338. Min Range: -11.3338

Max Act: 11.0213. Min Act: -0.1700

Data Index: 323609 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.9588. Min Act: -0.1700

Data Index: 6964412 (Open Web Text)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.9588. Min Act: -0.1700

Data Index: 6783988 (Open Web Text)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.8963. Min Act: -0.1700

Data Index: 5559833 (Open Web Text)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.9588. Min Act: -0.1700

Data Index: 2490640 (Open Web Text)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.8338. Min Act: -0.1700

Data Index: 4256806 (Open Web Text)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.8338. Min Act: -0.1700

Data Index: 315678 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.8338. Min Act: -0.1700

Data Index: 1972212 (Open Web Text)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.8338. Min Act: -0.1700

Data Index: 2490638 (Open Web Text)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.8338. Min Act: -0.1700

Data Index: 2490635 (Open Web Text)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.7713. Min Act: -0.1700

Data Index: 7726573 (Open Web Text)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.7713. Min Act: -0.1700

Data Index: 2490634 (Open Web Text)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.7713. Min Act: -0.1700

Data Index: 2490643 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.7088. Min Act: -0.1700

Data Index: 7221754 (Open Web Text)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.7713. Min Act: -0.1700

Data Index: 2965914 (Open Web Text)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.7088. Min Act: -0.1700

Data Index: 6119384 (Open Web Text)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 11.3338. Min Range: -11.3338

Max Act: 10.6463. Min Act: -0.1700

Data Index: 2490636 (Open Web Text)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #19