Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 6127 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0152. Min Range: -1.0152

Max Act: 1.0152. Min Act: -0.0000

Data Index: 369905 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 1.0152. Min Range: -1.0152

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1158560 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1126011 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.9477. Min Act: -0.0000

Data Index: 977493 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.9473. Min Act: -0.0000

Data Index: 675111 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.8990. Min Act: -0.0000

Data Index: 565239 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.9188. Min Act: -0.0000

Data Index: 574821 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.9097. Min Act: -0.0000

Data Index: 514424 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1276265 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1195752 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.8152. Min Act: -0.0000

Data Index: 285296 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.8656. Min Act: -0.0000

Data Index: 265594 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.7370. Min Act: -0.0000

Data Index: 173879 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.7739. Min Act: -0.0000

Data Index: 740746 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.8165. Min Act: -0.0000

Data Index: 259983 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1072173 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.7580. Min Act: -0.0000

Data Index: 85523 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.7528. Min Act: -0.0000

Data Index: 118108 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.7499. Min Act: -0.0000

Data Index: 230497 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.0152. Min Range: -1.0152

Max Act: 0.7216. Min Act: -0.0000

Data Index: 937391 (C4 (Web Text))

Max Activating Token Index: 169