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

Dataset: Open Web Text

Neuron 1449 in Layer 6

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: 3.3969. Min Range: -3.3969

Max Act: 3.3969. Min Act: -0.1700

Data Index: 6518187 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3969. Min Act: -0.1700

Data Index: 3951659 (Open Web Text)

Max Activating Token Index: 129

Text #2

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3739. Min Act: -0.1700

Data Index: 6958865 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3649. Min Act: -0.1700

Data Index: 1189028 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3758. Min Act: -0.1700

Data Index: 3136130 (Open Web Text)

Max Activating Token Index: 906

Text #5

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3509. Min Act: -0.1700

Data Index: 3523590 (Open Web Text)

Max Activating Token Index: 559

Text #6

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3467. Min Act: -0.1700

Data Index: 1938472 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3570. Min Act: -0.1700

Data Index: 2560872 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3680. Min Act: -0.1700

Data Index: 5116515 (Open Web Text)

Max Activating Token Index: 598

Text #9

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3212. Min Act: -0.1700

Data Index: 3962928 (Open Web Text)

Max Activating Token Index: 261

Text #10

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3352. Min Act: -0.1700

Data Index: 7433767 (Open Web Text)

Max Activating Token Index: 128

Text #11

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3273. Min Act: -0.1700

Data Index: 2474597 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3367. Min Act: -0.1700

Data Index: 737836 (Open Web Text)

Max Activating Token Index: 672

Text #13

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3199. Min Act: -0.1700

Data Index: 5228624 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3103. Min Act: -0.1700

Data Index: 4686518 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3085. Min Act: -0.1700

Data Index: 4560331 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2998. Min Act: -0.1700

Data Index: 5341599 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2987. Min Act: -0.1700

Data Index: 256536 (Open Web Text)

Max Activating Token Index: 897

Text #18

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.2707. Min Act: -0.1700

Data Index: 2773274 (Open Web Text)

Max Activating Token Index: 875

Text #19

Max Range: 3.3969. Min Range: -3.3969

Max Act: 3.3023. Min Act: -0.1700

Data Index: 1738938 (Open Web Text)

Max Activating Token Index: 832