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

Dataset: Open Web Text

Neuron 661 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: 5.4264. Min Range: -5.4264

Max Act: 5.4264. Min Act: -0.1700

Data Index: 5571567 (Open Web Text)

Max Activating Token Index: 306

Text #1

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.1438. Min Act: -0.1700

Data Index: 7046303 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.1726. Min Act: -0.1700

Data Index: 2369673 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.1234. Min Act: -0.1700

Data Index: 8357496 (Open Web Text)

Max Activating Token Index: 783

Text #4

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0457. Min Act: -0.1700

Data Index: 7280739 (Open Web Text)

Max Activating Token Index: 740

Text #5

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0522. Min Act: -0.1700

Data Index: 2239443 (Open Web Text)

Max Activating Token Index: 201

Text #6

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0388. Min Act: -0.1700

Data Index: 3495477 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0287. Min Act: -0.1700

Data Index: 1352979 (Open Web Text)

Max Activating Token Index: 935

Text #8

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0366. Min Act: -0.1700

Data Index: 2302087 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0225. Min Act: -0.1700

Data Index: 743931 (Open Web Text)

Max Activating Token Index: 222

Text #10

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0483. Min Act: -0.1700

Data Index: 7362886 (Open Web Text)

Max Activating Token Index: 677

Text #11

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.9890. Min Act: -0.1700

Data Index: 3104456 (Open Web Text)

Max Activating Token Index: 519

Text #12

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0400. Min Act: -0.1700

Data Index: 3738721 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.9962. Min Act: -0.1700

Data Index: 4359496 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.9897. Min Act: -0.1700

Data Index: 6187532 (Open Web Text)

Max Activating Token Index: 410

Text #15

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0173. Min Act: -0.1700

Data Index: 3715416 (Open Web Text)

Max Activating Token Index: 650

Text #16

Max Range: 5.4264. Min Range: -5.4264

Max Act: 4.9973. Min Act: -0.1700

Data Index: 4296782 (Open Web Text)

Max Activating Token Index: 752

Text #17

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0124. Min Act: -0.1700

Data Index: 4544228 (Open Web Text)

Max Activating Token Index: 74

Text #18

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0177. Min Act: -0.1700

Data Index: 6085730 (Open Web Text)

Max Activating Token Index: 245

Text #19

Max Range: 5.4264. Min Range: -5.4264

Max Act: 5.0051. Min Act: -0.1700

Data Index: 1157954 (Open Web Text)

Max Activating Token Index: 347