< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 5046 in Layer 26

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.2535. Min Act: -0.1700

Data Index: 4394673 (Open Web Text)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.1910. Min Act: -0.1700

Data Index: 2507667 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.1910. Min Act: -0.1700

Data Index: 2112277 (Open Web Text)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.0660. Min Act: -0.1700

Data Index: 3506114 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.0660. Min Act: -0.1700

Data Index: 1969365 (Open Web Text)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.0660. Min Act: -0.1700

Data Index: 3935148 (Open Web Text)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.0660. Min Act: -0.1700

Data Index: 6771122 (Open Web Text)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.0660. Min Act: -0.1700

Data Index: 321571 (Open Web Text)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.0035. Min Act: -0.1700

Data Index: 6211155 (Open Web Text)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.9410. Min Act: -0.1700

Data Index: 4109139 (Open Web Text)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.2535. Min Range: -10.2535

Max Act: 10.0035. Min Act: -0.1700

Data Index: 6333676 (Open Web Text)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.9410. Min Act: -0.1700

Data Index: 6997889 (Open Web Text)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.9410. Min Act: -0.1700

Data Index: 3420074 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.9410. Min Act: -0.1700

Data Index: 669803 (Open Web Text)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.8785. Min Act: -0.1700

Data Index: 4109141 (Open Web Text)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.8785. Min Act: -0.1700

Data Index: 5565071 (Open Web Text)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.8785. Min Act: -0.1700

Data Index: 5824368 (Open Web Text)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.8785. Min Act: -0.1700

Data Index: 4886371 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.7535. Min Act: -0.1700

Data Index: 4885617 (Open Web Text)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.2535. Min Range: -10.2535

Max Act: 9.7535. Min Act: -0.1700

Data Index: 2727316 (Open Web Text)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #19