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

Dataset: Open Web Text

Neuron 560 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.1703. Min Act: -0.1700

Data Index: 5666559 (Open Web Text)

Max Activating Token Index: 265

Text #1

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.1590. Min Act: -0.1700

Data Index: 5296949 (Open Web Text)

Max Activating Token Index: 610

Text #2

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.1192. Min Act: -0.1700

Data Index: 7581108 (Open Web Text)

Max Activating Token Index: 472

Text #3

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.1208. Min Act: -0.1700

Data Index: 1744070 (Open Web Text)

Max Activating Token Index: 901

Text #4

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0924. Min Act: -0.1700

Data Index: 2136384 (Open Web Text)

Max Activating Token Index: 494

Text #5

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.1193. Min Act: -0.1700

Data Index: 5353770 (Open Web Text)

Max Activating Token Index: 537

Text #6

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.1001. Min Act: -0.1700

Data Index: 8483004 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0919. Min Act: -0.1700

Data Index: 5509727 (Open Web Text)

Max Activating Token Index: 215

Text #8

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0896. Min Act: -0.1699

Data Index: 8641076 (Open Web Text)

Max Activating Token Index: 628

Text #9

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0722. Min Act: -0.1700

Data Index: 8326070 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0531. Min Act: -0.1700

Data Index: 3068193 (Open Web Text)

Max Activating Token Index: 630

Text #11

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0738. Min Act: -0.1700

Data Index: 1046347 (Open Web Text)

Max Activating Token Index: 180

Text #12

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0566. Min Act: -0.1700

Data Index: 3056894 (Open Web Text)

Max Activating Token Index: 51

Text #13

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0567. Min Act: -0.1700

Data Index: 6782208 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0362. Min Act: -0.1693

Data Index: 7393013 (Open Web Text)

Max Activating Token Index: 744

Text #15

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0283. Min Act: -0.1700

Data Index: 4318843 (Open Web Text)

Max Activating Token Index: 583

Text #16

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0266. Min Act: -0.1699

Data Index: 5832824 (Open Web Text)

Max Activating Token Index: 714

Text #17

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0563. Min Act: -0.1700

Data Index: 7502305 (Open Web Text)

Max Activating Token Index: 653

Text #18

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0212. Min Act: -0.1700

Data Index: 3099504 (Open Web Text)

Max Activating Token Index: 787

Text #19

Max Range: 3.1703. Min Range: -3.1703

Max Act: 3.0584. Min Act: -0.1700

Data Index: 3541446 (Open Web Text)

Max Activating Token Index: 575