Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2518 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.8184. Min Act: -0.0000

Data Index: 446620 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1322913 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.7187. Min Act: -0.0000

Data Index: 291045 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1042262 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6862. Min Act: -0.0000

Data Index: 267357 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.5975. Min Act: -0.0001

Data Index: 138690 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6514. Min Act: -0.0000

Data Index: 903149 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6891. Min Act: -0.0000

Data Index: 199334 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6170. Min Act: -0.0001

Data Index: 1294985 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6176. Min Act: -0.0000

Data Index: 107426 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6259. Min Act: -0.0001

Data Index: 983923 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6049. Min Act: -0.0001

Data Index: 456326 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.5825. Min Act: -0.0001

Data Index: 933324 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.5932. Min Act: -0.0000

Data Index: 235226 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.6140. Min Act: -0.0000

Data Index: 668042 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.5856. Min Act: -0.0000

Data Index: 625987 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.5956. Min Act: -0.0000

Data Index: 401196 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1150945 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.5744. Min Act: -0.0000

Data Index: 536478 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.8184. Min Range: -0.8184

Max Act: 0.5698. Min Act: -0.0000

Data Index: 378495 (C4 (Web Text))

Max Activating Token Index: 676