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

Dataset: Open Web Text

Neuron 13 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: 3.4922. Min Range: -3.4922

Max Act: 3.4922. Min Act: -0.1700

Data Index: 554868 (Open Web Text)

Max Activating Token Index: 45

Text #1

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.4059. Min Act: -0.1700

Data Index: 5536018 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.4251. Min Act: -0.1700

Data Index: 1295613 (Open Web Text)

Max Activating Token Index: 337

Text #3

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.4041. Min Act: -0.1700

Data Index: 1171579 (Open Web Text)

Max Activating Token Index: 369

Text #4

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.4275. Min Act: -0.1700

Data Index: 5556947 (Open Web Text)

Max Activating Token Index: 501

Text #5

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3675. Min Act: -0.1700

Data Index: 2987625 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.4376. Min Act: -0.1700

Data Index: 8252745 (Open Web Text)

Max Activating Token Index: 181

Text #7

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3817. Min Act: -0.1700

Data Index: 3321397 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3851. Min Act: -0.1700

Data Index: 3234579 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3792. Min Act: -0.1700

Data Index: 7513205 (Open Web Text)

Max Activating Token Index: 256

Text #10

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3190. Min Act: -0.1700

Data Index: 3045129 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3014. Min Act: -0.1700

Data Index: 379159 (Open Web Text)

Max Activating Token Index: 925

Text #12

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3542. Min Act: -0.1700

Data Index: 7087355 (Open Web Text)

Max Activating Token Index: 701

Text #13

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3273. Min Act: -0.1700

Data Index: 5992782 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3699. Min Act: -0.1700

Data Index: 8152166 (Open Web Text)

Max Activating Token Index: 691

Text #15

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3628. Min Act: -0.1700

Data Index: 6751384 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3434. Min Act: -0.1700

Data Index: 269568 (Open Web Text)

Max Activating Token Index: 799

Text #17

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3322. Min Act: -0.1700

Data Index: 826174 (Open Web Text)

Max Activating Token Index: 735

Text #18

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3255. Min Act: -0.1700

Data Index: 7440248 (Open Web Text)

Max Activating Token Index: 870

Text #19

Max Range: 3.4922. Min Range: -3.4922

Max Act: 3.3290. Min Act: -0.1700

Data Index: 6340689 (Open Web Text)

Max Activating Token Index: 784