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

Dataset: Open Web Text

Neuron 1928 in Layer 2

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: 3.3027. Min Range: -3.3027

Max Act: 3.2765. Min Act: -0.1700

Data Index: 6485479 (Open Web Text)

Max Activating Token Index: 474

Text #1

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2821. Min Act: -0.1700

Data Index: 5029523 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.3027. Min Act: -0.1700

Data Index: 5718213 (Open Web Text)

Max Activating Token Index: 900

Text #3

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2616. Min Act: -0.1700

Data Index: 3404150 (Open Web Text)

Max Activating Token Index: 365

Text #4

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2520. Min Act: -0.1700

Data Index: 7537318 (Open Web Text)

Max Activating Token Index: 561

Text #5

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2492. Min Act: -0.1700

Data Index: 4530757 (Open Web Text)

Max Activating Token Index: 269

Text #6

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2765. Min Act: -0.1700

Data Index: 1426977 (Open Web Text)

Max Activating Token Index: 391

Text #7

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2676. Min Act: -0.1700

Data Index: 2198344 (Open Web Text)

Max Activating Token Index: 549

Text #8

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2723. Min Act: -0.1700

Data Index: 8128189 (Open Web Text)

Max Activating Token Index: 821

Text #9

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2567. Min Act: -0.1700

Data Index: 3462269 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2346. Min Act: -0.1700

Data Index: 6294166 (Open Web Text)

Max Activating Token Index: 950

Text #11

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2409. Min Act: -0.1700

Data Index: 6230019 (Open Web Text)

Max Activating Token Index: 372

Text #12

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2355. Min Act: -0.1700

Data Index: 8128199 (Open Web Text)

Max Activating Token Index: 629

Text #13

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2491. Min Act: -0.1700

Data Index: 2222323 (Open Web Text)

Max Activating Token Index: 744

Text #14

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2324. Min Act: -0.1700

Data Index: 7537322 (Open Web Text)

Max Activating Token Index: 879

Text #15

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2436. Min Act: -0.1700

Data Index: 4475268 (Open Web Text)

Max Activating Token Index: 983

Text #16

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2539. Min Act: -0.1700

Data Index: 1401047 (Open Web Text)

Max Activating Token Index: 445

Text #17

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2426. Min Act: -0.1700

Data Index: 6805992 (Open Web Text)

Max Activating Token Index: 185

Text #18

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2488. Min Act: -0.1700

Data Index: 1737643 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2350. Min Act: -0.1700

Data Index: 2397680 (Open Web Text)

Max Activating Token Index: 1023