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

Dataset: Open Web Text

Neuron 1921 in Layer 5

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: 4.8786. Min Range: -4.8786

Max Act: 4.8786. Min Act: -0.1700

Data Index: 1874304 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7998. Min Act: -0.1700

Data Index: 665336 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7864. Min Act: -0.1700

Data Index: 5582992 (Open Web Text)

Max Activating Token Index: 36

Text #3

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7888. Min Act: -0.1700

Data Index: 7753881 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7902. Min Act: -0.1700

Data Index: 2650590 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7720. Min Act: -0.1700

Data Index: 4074978 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7793. Min Act: -0.1700

Data Index: 3152524 (Open Web Text)

Max Activating Token Index: 732

Text #7

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7209. Min Act: -0.1700

Data Index: 6316798 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7252. Min Act: -0.1700

Data Index: 2535611 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7358. Min Act: -0.1700

Data Index: 488556 (Open Web Text)

Max Activating Token Index: 251

Text #10

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7451. Min Act: -0.1700

Data Index: 1297916 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7775. Min Act: -0.1700

Data Index: 197239 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7369. Min Act: -0.1700

Data Index: 3951703 (Open Web Text)

Max Activating Token Index: 860

Text #13

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7100. Min Act: -0.1700

Data Index: 3534459 (Open Web Text)

Max Activating Token Index: 382

Text #14

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7228. Min Act: -0.1700

Data Index: 5082630 (Open Web Text)

Max Activating Token Index: 965

Text #15

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7069. Min Act: -0.1700

Data Index: 609231 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7425. Min Act: -0.1700

Data Index: 4395323 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.7195. Min Act: -0.1700

Data Index: 449840 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.6985. Min Act: -0.1700

Data Index: 3049398 (Open Web Text)

Max Activating Token Index: 1001

Text #19

Max Range: 4.8786. Min Range: -4.8786

Max Act: 4.6947. Min Act: -0.1700

Data Index: 225655 (Open Web Text)

Max Activating Token Index: 441