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

Dataset: Open Web Text

Neuron 2459 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: 3.7865. Min Range: -3.7865

Max Act: 3.7813. Min Act: -0.1700

Data Index: 6216119 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7865. Min Act: -0.1700

Data Index: 7438165 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7727. Min Act: -0.1700

Data Index: 834921 (Open Web Text)

Max Activating Token Index: 367

Text #3

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7526. Min Act: -0.1700

Data Index: 3156906 (Open Web Text)

Max Activating Token Index: 104

Text #4

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7774. Min Act: -0.1700

Data Index: 2937631 (Open Web Text)

Max Activating Token Index: 378

Text #5

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7115. Min Act: -0.1700

Data Index: 3059010 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6894. Min Act: -0.1700

Data Index: 4385593 (Open Web Text)

Max Activating Token Index: 89

Text #7

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6769. Min Act: -0.1700

Data Index: 3173379 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6929. Min Act: -0.1700

Data Index: 2923664 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6212. Min Act: -0.1700

Data Index: 8787529 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6657. Min Act: -0.1700

Data Index: 8702114 (Open Web Text)

Max Activating Token Index: 938

Text #11

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6560. Min Act: -0.1700

Data Index: 7438167 (Open Web Text)

Max Activating Token Index: 640

Text #12

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6869. Min Act: -0.1700

Data Index: 7438164 (Open Web Text)

Max Activating Token Index: 996

Text #13

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6625. Min Act: -0.1700

Data Index: 6005546 (Open Web Text)

Max Activating Token Index: 993

Text #14

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6430. Min Act: -0.1700

Data Index: 8302784 (Open Web Text)

Max Activating Token Index: 747

Text #15

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6203. Min Act: -0.1700

Data Index: 145373 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6193. Min Act: -0.1700

Data Index: 1880940 (Open Web Text)

Max Activating Token Index: 291

Text #17

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6539. Min Act: -0.1700

Data Index: 4776369 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6169. Min Act: -0.1700

Data Index: 8169600 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5964. Min Act: -0.1700

Data Index: 2899196 (Open Web Text)

Max Activating Token Index: 508