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

Dataset: Open Web Text

Neuron 126 in Layer 5

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: 3.5524. Min Range: -3.5524

Max Act: 3.5524. Min Act: -0.1700

Data Index: 474952 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.5432. Min Act: -0.1700

Data Index: 8078615 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4694. Min Act: -0.1700

Data Index: 4546616 (Open Web Text)

Max Activating Token Index: 989

Text #3

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4642. Min Act: -0.1700

Data Index: 1947096 (Open Web Text)

Max Activating Token Index: 943

Text #4

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4690. Min Act: -0.1700

Data Index: 6614948 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4706. Min Act: -0.1700

Data Index: 460092 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4387. Min Act: -0.1700

Data Index: 8125402 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4481. Min Act: -0.1700

Data Index: 3904020 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4256. Min Act: -0.1700

Data Index: 71479 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4250. Min Act: -0.1700

Data Index: 99721 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4475. Min Act: -0.1700

Data Index: 448526 (Open Web Text)

Max Activating Token Index: 606

Text #11

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4298. Min Act: -0.1700

Data Index: 8422099 (Open Web Text)

Max Activating Token Index: 118

Text #12

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4301. Min Act: -0.1700

Data Index: 8049004 (Open Web Text)

Max Activating Token Index: 692

Text #13

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4327. Min Act: -0.1700

Data Index: 1605648 (Open Web Text)

Max Activating Token Index: 289

Text #14

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4136. Min Act: -0.1700

Data Index: 3199078 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4147. Min Act: -0.1700

Data Index: 994423 (Open Web Text)

Max Activating Token Index: 882

Text #16

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4252. Min Act: -0.1700

Data Index: 313443 (Open Web Text)

Max Activating Token Index: 35

Text #17

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4128. Min Act: -0.1700

Data Index: 7974585 (Open Web Text)

Max Activating Token Index: 907

Text #18

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.4055. Min Act: -0.1700

Data Index: 1844322 (Open Web Text)

Max Activating Token Index: 991

Text #19

Max Range: 3.5524. Min Range: -3.5524

Max Act: 3.3944. Min Act: -0.1700

Data Index: 7322707 (Open Web Text)

Max Activating Token Index: 423