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

Dataset: Open Web Text

Neuron 1703 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: 3.0328. Min Range: -3.0328

Max Act: 3.0088. Min Act: -0.1700

Data Index: 5133142 (Open Web Text)

Max Activating Token Index: 567

Text #1

Max Range: 3.0328. Min Range: -3.0328

Max Act: 3.0328. Min Act: -0.1700

Data Index: 900552 (Open Web Text)

Max Activating Token Index: 529

Text #2

Max Range: 3.0328. Min Range: -3.0328

Max Act: 3.0270. Min Act: -0.1700

Data Index: 2826850 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 3.0328. Min Range: -3.0328

Max Act: 3.0201. Min Act: -0.1700

Data Index: 3982787 (Open Web Text)

Max Activating Token Index: 540

Text #4

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9928. Min Act: -0.1700

Data Index: 7946468 (Open Web Text)

Max Activating Token Index: 940

Text #5

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9863. Min Act: -0.1700

Data Index: 1508339 (Open Web Text)

Max Activating Token Index: 267

Text #6

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9786. Min Act: -0.1700

Data Index: 908564 (Open Web Text)

Max Activating Token Index: 380

Text #7

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9914. Min Act: -0.1700

Data Index: 7109424 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9919. Min Act: -0.1700

Data Index: 6002019 (Open Web Text)

Max Activating Token Index: 267

Text #9

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9283. Min Act: -0.1700

Data Index: 4938006 (Open Web Text)

Max Activating Token Index: 415

Text #10

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9334. Min Act: -0.1700

Data Index: 4479088 (Open Web Text)

Max Activating Token Index: 849

Text #11

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9410. Min Act: -0.1700

Data Index: 5457467 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9372. Min Act: -0.1700

Data Index: 965033 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9326. Min Act: -0.1700

Data Index: 6856079 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9223. Min Act: -0.1700

Data Index: 3527601 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9203. Min Act: -0.1700

Data Index: 7204610 (Open Web Text)

Max Activating Token Index: 778

Text #16

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9195. Min Act: -0.1700

Data Index: 3604062 (Open Web Text)

Max Activating Token Index: 597

Text #17

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9200. Min Act: -0.1700

Data Index: 4873676 (Open Web Text)

Max Activating Token Index: 578

Text #18

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9106. Min Act: -0.1700

Data Index: 8237929 (Open Web Text)

Max Activating Token Index: 227

Text #19

Max Range: 3.0328. Min Range: -3.0328

Max Act: 2.9077. Min Act: -0.1700

Data Index: 315466 (Open Web Text)

Max Activating Token Index: 756