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

Dataset: Open Web Text

Neuron 2712 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: 4.7176. Min Range: -4.7176

Max Act: 4.7176. Min Act: -0.1700

Data Index: 8721370 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6568. Min Act: -0.1700

Data Index: 2233140 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6738. Min Act: -0.1700

Data Index: 1481105 (Open Web Text)

Max Activating Token Index: 461

Text #3

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6742. Min Act: -0.1700

Data Index: 7887836 (Open Web Text)

Max Activating Token Index: 160

Text #4

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6794. Min Act: -0.1700

Data Index: 4415456 (Open Web Text)

Max Activating Token Index: 122

Text #5

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6465. Min Act: -0.1700

Data Index: 7407406 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5880. Min Act: -0.1700

Data Index: 7556403 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6265. Min Act: -0.1700

Data Index: 815148 (Open Web Text)

Max Activating Token Index: 379

Text #8

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5956. Min Act: -0.1700

Data Index: 4463307 (Open Web Text)

Max Activating Token Index: 29

Text #9

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6045. Min Act: -0.1700

Data Index: 7683042 (Open Web Text)

Max Activating Token Index: 132

Text #10

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6070. Min Act: -0.1700

Data Index: 3908967 (Open Web Text)

Max Activating Token Index: 953

Text #11

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.6234. Min Act: -0.1700

Data Index: 233775 (Open Web Text)

Max Activating Token Index: 205

Text #12

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5492. Min Act: -0.1700

Data Index: 7664787 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5816. Min Act: -0.1700

Data Index: 7743106 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5826. Min Act: -0.1700

Data Index: 5252044 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5513. Min Act: -0.1700

Data Index: 1400598 (Open Web Text)

Max Activating Token Index: 64

Text #16

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5406. Min Act: -0.1700

Data Index: 2450174 (Open Web Text)

Max Activating Token Index: 114

Text #17

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5336. Min Act: -0.1700

Data Index: 1688413 (Open Web Text)

Max Activating Token Index: 84

Text #18

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5366. Min Act: -0.1700

Data Index: 7743097 (Open Web Text)

Max Activating Token Index: 861

Text #19

Max Range: 4.7176. Min Range: -4.7176

Max Act: 4.5540. Min Act: -0.1700

Data Index: 5190511 (Open Web Text)

Max Activating Token Index: 330