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

Dataset: Open Web Text

Neuron 175 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: 3.9382. Min Range: -3.9382

Max Act: 3.9382. Min Act: -0.1700

Data Index: 5666318 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.8378. Min Act: -0.1700

Data Index: 5932643 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.8205. Min Act: -0.1700

Data Index: 8520076 (Open Web Text)

Max Activating Token Index: 248

Text #3

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.7879. Min Act: -0.1700

Data Index: 8070815 (Open Web Text)

Max Activating Token Index: 821

Text #4

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.7351. Min Act: -0.1700

Data Index: 4932334 (Open Web Text)

Max Activating Token Index: 982

Text #5

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.7464. Min Act: -0.1700

Data Index: 1171709 (Open Web Text)

Max Activating Token Index: 628

Text #6

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.7346. Min Act: -0.1700

Data Index: 2611368 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.7237. Min Act: -0.1700

Data Index: 7614902 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.7092. Min Act: -0.1700

Data Index: 5156221 (Open Web Text)

Max Activating Token Index: 136

Text #9

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6884. Min Act: -0.1700

Data Index: 2633702 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6807. Min Act: -0.1700

Data Index: 1132045 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6800. Min Act: -0.1700

Data Index: 2076357 (Open Web Text)

Max Activating Token Index: 1004

Text #12

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6855. Min Act: -0.1700

Data Index: 1288658 (Open Web Text)

Max Activating Token Index: 212

Text #13

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6869. Min Act: -0.1700

Data Index: 2109382 (Open Web Text)

Max Activating Token Index: 367

Text #14

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6251. Min Act: -0.1700

Data Index: 1644701 (Open Web Text)

Max Activating Token Index: 900

Text #15

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6427. Min Act: -0.1700

Data Index: 5725442 (Open Web Text)

Max Activating Token Index: 602

Text #16

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6317. Min Act: -0.1700

Data Index: 3781373 (Open Web Text)

Max Activating Token Index: 193

Text #17

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6699. Min Act: -0.1700

Data Index: 6761118 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6578. Min Act: -0.1700

Data Index: 3065311 (Open Web Text)

Max Activating Token Index: 349

Text #19

Max Range: 3.9382. Min Range: -3.9382

Max Act: 3.6073. Min Act: -0.1700

Data Index: 2701297 (Open Web Text)

Max Activating Token Index: 803