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

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

Neuron 3780 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.4431. Min Act: -0.0000

Data Index: 230021 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3968. Min Act: -0.0001

Data Index: 30399 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.4462. Min Act: -0.0000

Data Index: 674846 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3108. Min Act: -0.0000

Data Index: 372462 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3966. Min Act: -0.0001

Data Index: 125327 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1019505 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1256741 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3430. Min Act: -0.0000

Data Index: 557969 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3133. Min Act: -0.0000

Data Index: 368528 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3198. Min Act: -0.0000

Data Index: 905222 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3305. Min Act: -0.0001

Data Index: 677667 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3146. Min Act: -0.0001

Data Index: 1308173 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3117. Min Act: -0.0000

Data Index: 736197 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1198577 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1256972 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3211. Min Act: -0.0000

Data Index: 881253 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3189. Min Act: -0.0000

Data Index: 592402 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1039585 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3004. Min Act: -0.0001

Data Index: 933309 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2874. Min Act: -0.0000

Data Index: 650688 (C4 (Web Text))

Max Activating Token Index: 169