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

Dataset: Open Web Text

Neuron 2834 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: 6.1170. Min Range: -6.1170

Max Act: 6.1170. Min Act: -0.1700

Data Index: 6970081 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7898. Min Act: -0.1700

Data Index: 7497669 (Open Web Text)

Max Activating Token Index: 906

Text #2

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7930. Min Act: -0.1700

Data Index: 2319669 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.6644. Min Act: -0.1700

Data Index: 5643571 (Open Web Text)

Max Activating Token Index: 433

Text #4

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.8135. Min Act: -0.1700

Data Index: 4741789 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7260. Min Act: -0.1700

Data Index: 7011279 (Open Web Text)

Max Activating Token Index: 128

Text #6

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7910. Min Act: -0.1700

Data Index: 5193532 (Open Web Text)

Max Activating Token Index: 358

Text #7

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7972. Min Act: -0.1700

Data Index: 887250 (Open Web Text)

Max Activating Token Index: 208

Text #8

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.6707. Min Act: -0.1700

Data Index: 4654615 (Open Web Text)

Max Activating Token Index: 596

Text #9

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.6559. Min Act: -0.1700

Data Index: 7669556 (Open Web Text)

Max Activating Token Index: 576

Text #10

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7395. Min Act: -0.1700

Data Index: 1981858 (Open Web Text)

Max Activating Token Index: 623

Text #11

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.6698. Min Act: -0.1700

Data Index: 4518854 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.6650. Min Act: -0.1700

Data Index: 2108029 (Open Web Text)

Max Activating Token Index: 474

Text #13

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.5904. Min Act: -0.1700

Data Index: 3244974 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.6175. Min Act: -0.1700

Data Index: 3662157 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7612. Min Act: -0.1700

Data Index: 3575837 (Open Web Text)

Max Activating Token Index: 499

Text #16

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7018. Min Act: -0.1700

Data Index: 37730 (Open Web Text)

Max Activating Token Index: 497

Text #17

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.7175. Min Act: -0.1700

Data Index: 1299914 (Open Web Text)

Max Activating Token Index: 586

Text #18

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.5260. Min Act: -0.1700

Data Index: 4244058 (Open Web Text)

Max Activating Token Index: 617

Text #19

Max Range: 6.1170. Min Range: -6.1170

Max Act: 5.6315. Min Act: -0.1700

Data Index: 5308151 (Open Web Text)

Max Activating Token Index: 347