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

Dataset: Open Web Text

Neuron 1712 in Layer 4

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: 3.4725. Min Range: -3.4725

Max Act: 3.4725. Min Act: -0.1700

Data Index: 5729580 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.4360. Min Act: -0.1700

Data Index: 8829601 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.4089. Min Act: -0.1700

Data Index: 2890725 (Open Web Text)

Max Activating Token Index: 446

Text #3

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.3894. Min Act: -0.1700

Data Index: 6746248 (Open Web Text)

Max Activating Token Index: 445

Text #4

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.3293. Min Act: -0.1700

Data Index: 1564362 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.3385. Min Act: -0.1700

Data Index: 1236895 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.3155. Min Act: -0.1700

Data Index: 3336497 (Open Web Text)

Max Activating Token Index: 425

Text #7

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2993. Min Act: -0.1700

Data Index: 1012269 (Open Web Text)

Max Activating Token Index: 296

Text #8

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2887. Min Act: -0.1700

Data Index: 4708796 (Open Web Text)

Max Activating Token Index: 731

Text #9

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2748. Min Act: -0.1700

Data Index: 8554214 (Open Web Text)

Max Activating Token Index: 879

Text #10

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2918. Min Act: -0.1700

Data Index: 6735509 (Open Web Text)

Max Activating Token Index: 974

Text #11

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2624. Min Act: -0.1700

Data Index: 6116980 (Open Web Text)

Max Activating Token Index: 627

Text #12

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2539. Min Act: -0.1700

Data Index: 3792540 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2697. Min Act: -0.1700

Data Index: 4660131 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2423. Min Act: -0.1700

Data Index: 2610075 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2487. Min Act: -0.1700

Data Index: 7576939 (Open Web Text)

Max Activating Token Index: 284

Text #16

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2425. Min Act: -0.1700

Data Index: 1645586 (Open Web Text)

Max Activating Token Index: 363

Text #17

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2554. Min Act: -0.1700

Data Index: 4882962 (Open Web Text)

Max Activating Token Index: 850

Text #18

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2512. Min Act: -0.1700

Data Index: 4694037 (Open Web Text)

Max Activating Token Index: 372

Text #19

Max Range: 3.4725. Min Range: -3.4725

Max Act: 3.2374. Min Act: -0.1700

Data Index: 4680405 (Open Web Text)

Max Activating Token Index: 449