< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6366 in Layer 32

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.3647. Min Range: -10.3647

Max Act: 10.3647. Min Act: -0.1700

Data Index: 7970389 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.6772. Min Act: -0.1700

Data Index: 8053460 (Open Web Text)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.6147. Min Act: -0.1700

Data Index: 1753063 (Open Web Text)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.6147. Min Act: -0.1700

Data Index: 1219748 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.4897. Min Act: -0.1700

Data Index: 475299 (Open Web Text)

Max Activating Token Index: 769

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.4272. Min Act: -0.1700

Data Index: 405012 (Open Web Text)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.4272. Min Act: -0.1700

Data Index: 3750079 (Open Web Text)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.2397. Min Act: -0.1700

Data Index: 8670782 (Open Web Text)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.2397. Min Act: -0.1700

Data Index: 3187192 (Open Web Text)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.3022. Min Act: -0.1700

Data Index: 7234670 (Open Web Text)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.1772. Min Act: -0.1700

Data Index: 1147317 (Open Web Text)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.1772. Min Act: -0.1700

Data Index: 5479554 (Open Web Text)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.1772. Min Act: -0.1700

Data Index: 5749228 (Open Web Text)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.1147. Min Act: -0.1700

Data Index: 1393735 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.0522. Min Act: -0.1700

Data Index: 2571134 (Open Web Text)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.0522. Min Act: -0.1700

Data Index: 4641184 (Open Web Text)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.0522. Min Act: -0.1700

Data Index: 7767236 (Open Web Text)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.0522. Min Act: -0.1700

Data Index: 1587360 (Open Web Text)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.0522. Min Act: -0.1700

Data Index: 7814879 (Open Web Text)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.3647. Min Range: -10.3647

Max Act: 9.0522. Min Act: -0.1700

Data Index: 3208714 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #19