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

Dataset: Open Web Text

Neuron 1138 in Layer 2

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: 2.7692. Min Range: -2.7692

Max Act: 2.7692. Min Act: -0.1700

Data Index: 1665110 (Open Web Text)

Max Activating Token Index: 500

Text #1

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.7283. Min Act: -0.1700

Data Index: 2184672 (Open Web Text)

Max Activating Token Index: 760

Text #2

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.7428. Min Act: -0.1700

Data Index: 7374894 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.7323. Min Act: -0.1700

Data Index: 598904 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6599. Min Act: -0.1700

Data Index: 4763402 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6893. Min Act: -0.1700

Data Index: 6214349 (Open Web Text)

Max Activating Token Index: 246

Text #6

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6686. Min Act: -0.1700

Data Index: 970467 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6588. Min Act: -0.1700

Data Index: 4100440 (Open Web Text)

Max Activating Token Index: 423

Text #8

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6701. Min Act: -0.1700

Data Index: 247892 (Open Web Text)

Max Activating Token Index: 907

Text #9

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6596. Min Act: -0.1700

Data Index: 6621447 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6428. Min Act: -0.1700

Data Index: 5209366 (Open Web Text)

Max Activating Token Index: 874

Text #11

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6389. Min Act: -0.1700

Data Index: 3110643 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6184. Min Act: -0.1700

Data Index: 1876230 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6033. Min Act: -0.1700

Data Index: 4285102 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6392. Min Act: -0.1700

Data Index: 1921993 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6357. Min Act: -0.1700

Data Index: 1712321 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6293. Min Act: -0.1700

Data Index: 4012467 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6197. Min Act: -0.1700

Data Index: 3559881 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6485. Min Act: -0.1700

Data Index: 4749395 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.7692. Min Range: -2.7692

Max Act: 2.6261. Min Act: -0.1700

Data Index: 2509674 (Open Web Text)

Max Activating Token Index: 7