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

Dataset: Open Web Text

Neuron 273 in Layer 3

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: 3.7356. Min Range: -3.7356

Max Act: 3.7356. Min Act: -0.1700

Data Index: 274250 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.7297. Min Act: -0.1700

Data Index: 599880 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.7065. Min Act: -0.1700

Data Index: 1432415 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.7092. Min Act: -0.1700

Data Index: 8620889 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6960. Min Act: -0.1700

Data Index: 5586755 (Open Web Text)

Max Activating Token Index: 799

Text #5

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6939. Min Act: -0.1700

Data Index: 626761 (Open Web Text)

Max Activating Token Index: 894

Text #6

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6449. Min Act: -0.1700

Data Index: 6903699 (Open Web Text)

Max Activating Token Index: 742

Text #7

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6489. Min Act: -0.1700

Data Index: 4034560 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6731. Min Act: -0.1700

Data Index: 2931960 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6459. Min Act: -0.1700

Data Index: 2611431 (Open Web Text)

Max Activating Token Index: 893

Text #10

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6451. Min Act: -0.1700

Data Index: 1357223 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6714. Min Act: -0.1700

Data Index: 7966198 (Open Web Text)

Max Activating Token Index: 490

Text #12

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6318. Min Act: -0.1700

Data Index: 2319706 (Open Web Text)

Max Activating Token Index: 956

Text #13

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6381. Min Act: -0.1700

Data Index: 2201269 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6575. Min Act: -0.1700

Data Index: 7702368 (Open Web Text)

Max Activating Token Index: 955

Text #15

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6581. Min Act: -0.1700

Data Index: 1214961 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6286. Min Act: -0.1700

Data Index: 2414809 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6279. Min Act: -0.1700

Data Index: 201675 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6044. Min Act: -0.1700

Data Index: 3073992 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 3.7356. Min Range: -3.7356

Max Act: 3.6202. Min Act: -0.1700

Data Index: 4931176 (Open Web Text)

Max Activating Token Index: 26