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

Dataset: Open Web Text

Neuron 334 in Layer 6

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: 4.8383. Min Range: -4.8383

Max Act: 4.8383. Min Act: -0.1700

Data Index: 7890857 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7601. Min Act: -0.1700

Data Index: 3359446 (Open Web Text)

Max Activating Token Index: 657

Text #2

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7754. Min Act: -0.1700

Data Index: 2491545 (Open Web Text)

Max Activating Token Index: 222

Text #3

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7611. Min Act: -0.1700

Data Index: 6978056 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7746. Min Act: -0.1700

Data Index: 8660032 (Open Web Text)

Max Activating Token Index: 328

Text #5

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7571. Min Act: -0.1700

Data Index: 2668522 (Open Web Text)

Max Activating Token Index: 548

Text #6

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7577. Min Act: -0.1700

Data Index: 149416 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7418. Min Act: -0.1700

Data Index: 7458312 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7338. Min Act: -0.1700

Data Index: 7297969 (Open Web Text)

Max Activating Token Index: 216

Text #9

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7263. Min Act: -0.1700

Data Index: 3832052 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.7186. Min Act: -0.1700

Data Index: 1715499 (Open Web Text)

Max Activating Token Index: 341

Text #11

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6962. Min Act: -0.1700

Data Index: 3219750 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6816. Min Act: -0.1700

Data Index: 7256680 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6252. Min Act: -0.1700

Data Index: 5674052 (Open Web Text)

Max Activating Token Index: 300

Text #14

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6418. Min Act: -0.1700

Data Index: 4994232 (Open Web Text)

Max Activating Token Index: 930

Text #15

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6346. Min Act: -0.1700

Data Index: 1115253 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6564. Min Act: -0.1700

Data Index: 3372998 (Open Web Text)

Max Activating Token Index: 506

Text #17

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6560. Min Act: -0.1700

Data Index: 2434055 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6155. Min Act: -0.1700

Data Index: 3890691 (Open Web Text)

Max Activating Token Index: 320

Text #19

Max Range: 4.8383. Min Range: -4.8383

Max Act: 4.6183. Min Act: -0.1700

Data Index: 3891783 (Open Web Text)

Max Activating Token Index: 210