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

Dataset: Open Web Text

Neuron 567 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: 2.0938. Min Range: -2.0938

Max Act: 2.0938. Min Act: -0.1700

Data Index: 5582536 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0566. Min Act: -0.1700

Data Index: 8093847 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0216. Min Act: -0.1700

Data Index: 7670507 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0227. Min Act: -0.1700

Data Index: 8607620 (Open Web Text)

Max Activating Token Index: 527

Text #4

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0040. Min Act: -0.1700

Data Index: 6182365 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0003. Min Act: -0.1700

Data Index: 715417 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9870. Min Act: -0.1700

Data Index: 7885051 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 2.0938. Min Range: -2.0938

Max Act: 2.0025. Min Act: -0.1700

Data Index: 962198 (Open Web Text)

Max Activating Token Index: 586

Text #8

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9766. Min Act: -0.1700

Data Index: 8397796 (Open Web Text)

Max Activating Token Index: 1018

Text #9

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9933. Min Act: -0.1700

Data Index: 962196 (Open Web Text)

Max Activating Token Index: 145

Text #10

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9578. Min Act: -0.1700

Data Index: 336005 (Open Web Text)

Max Activating Token Index: 894

Text #11

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9449. Min Act: -0.1700

Data Index: 626370 (Open Web Text)

Max Activating Token Index: 901

Text #12

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9304. Min Act: -0.1700

Data Index: 2797512 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9671. Min Act: -0.1700

Data Index: 7399377 (Open Web Text)

Max Activating Token Index: 814

Text #14

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9372. Min Act: -0.1700

Data Index: 7866253 (Open Web Text)

Max Activating Token Index: 187

Text #15

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9314. Min Act: -0.1700

Data Index: 1142523 (Open Web Text)

Max Activating Token Index: 573

Text #16

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9288. Min Act: -0.1700

Data Index: 4433785 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9166. Min Act: -0.1700

Data Index: 4159756 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9236. Min Act: -0.1700

Data Index: 6437476 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 2.0938. Min Range: -2.0938

Max Act: 1.9130. Min Act: -0.1700

Data Index: 512034 (Open Web Text)

Max Activating Token Index: 290