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

Dataset: Open Web Text

Neuron 723 in Layer 1

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: 4.5921. Min Range: -4.5921

Max Act: 4.5851. Min Act: -0.1700

Data Index: 109511 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5637. Min Act: -0.1700

Data Index: 6427386 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5536. Min Act: -0.1700

Data Index: 3861203 (Open Web Text)

Max Activating Token Index: 800

Text #3

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5921. Min Act: -0.1700

Data Index: 2168659 (Open Web Text)

Max Activating Token Index: 353

Text #4

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5280. Min Act: -0.1700

Data Index: 7348504 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5443. Min Act: -0.1700

Data Index: 168086 (Open Web Text)

Max Activating Token Index: 748

Text #6

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5424. Min Act: -0.1700

Data Index: 7430451 (Open Web Text)

Max Activating Token Index: 485

Text #7

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5516. Min Act: -0.1700

Data Index: 7822639 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5350. Min Act: -0.1700

Data Index: 8678876 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5275. Min Act: -0.1700

Data Index: 3717902 (Open Web Text)

Max Activating Token Index: 626

Text #10

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5393. Min Act: -0.1700

Data Index: 2351116 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5495. Min Act: -0.1700

Data Index: 1396964 (Open Web Text)

Max Activating Token Index: 464

Text #12

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5360. Min Act: -0.1700

Data Index: 4298332 (Open Web Text)

Max Activating Token Index: 527

Text #13

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5062. Min Act: -0.1700

Data Index: 5298234 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5257. Min Act: -0.1700

Data Index: 4640407 (Open Web Text)

Max Activating Token Index: 626

Text #15

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5285. Min Act: -0.1700

Data Index: 714914 (Open Web Text)

Max Activating Token Index: 543

Text #16

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5147. Min Act: -0.1700

Data Index: 3959243 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5006. Min Act: -0.1700

Data Index: 1945366 (Open Web Text)

Max Activating Token Index: 888

Text #18

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5050. Min Act: -0.1700

Data Index: 1285327 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 4.5921. Min Range: -4.5921

Max Act: 4.5263. Min Act: -0.1700

Data Index: 578878 (Open Web Text)

Max Activating Token Index: 973