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

Dataset: Open Web Text

Neuron 315 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: 4.4945. Min Range: -4.4945

Max Act: 4.4945. Min Act: -0.1700

Data Index: 8142229 (Open Web Text)

Max Activating Token Index: 723

Text #1

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.2511. Min Act: -0.1700

Data Index: 8142230 (Open Web Text)

Max Activating Token Index: 109

Text #2

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.1725. Min Act: -0.1700

Data Index: 6867843 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.0950. Min Act: -0.1700

Data Index: 1632956 (Open Web Text)

Max Activating Token Index: 167

Text #4

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.1112. Min Act: -0.1700

Data Index: 6860884 (Open Web Text)

Max Activating Token Index: 326

Text #5

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.0241. Min Act: -0.1700

Data Index: 5554326 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.0090. Min Act: -0.1700

Data Index: 2968652 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.0487. Min Act: -0.1700

Data Index: 3638675 (Open Web Text)

Max Activating Token Index: 794

Text #8

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.0097. Min Act: -0.1700

Data Index: 5000701 (Open Web Text)

Max Activating Token Index: 180

Text #9

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.0156. Min Act: -0.1700

Data Index: 7079102 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 4.4945. Min Range: -4.4945

Max Act: 4.0172. Min Act: -0.1700

Data Index: 5696882 (Open Web Text)

Max Activating Token Index: 388

Text #11

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.9246. Min Act: -0.1700

Data Index: 1440049 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.9395. Min Act: -0.1700

Data Index: 5554318 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.9726. Min Act: -0.1700

Data Index: 5599031 (Open Web Text)

Max Activating Token Index: 911

Text #14

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.9382. Min Act: -0.1700

Data Index: 1028921 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.9156. Min Act: -0.1700

Data Index: 5721995 (Open Web Text)

Max Activating Token Index: 159

Text #16

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.9369. Min Act: -0.1700

Data Index: 4795993 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.9358. Min Act: -0.1700

Data Index: 8239520 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.8795. Min Act: -0.1700

Data Index: 5570496 (Open Web Text)

Max Activating Token Index: 823

Text #19

Max Range: 4.4945. Min Range: -4.4945

Max Act: 3.8679. Min Act: -0.1700

Data Index: 5811020 (Open Web Text)

Max Activating Token Index: 121