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

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

Neuron 3283 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1178404 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5808. Min Act: -0.0000

Data Index: 442958 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5488. Min Act: -0.0000

Data Index: 878976 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5648. Min Act: -0.0000

Data Index: 201906 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5454. Min Act: -0.0000

Data Index: 586693 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4589. Min Act: -0.0000

Data Index: 367135 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4635. Min Act: -0.0000

Data Index: 167848 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4833. Min Act: -0.0000

Data Index: 403014 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1048442 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4308. Min Act: -0.0000

Data Index: 213682 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4592. Min Act: -0.0000

Data Index: 110259 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4381. Min Act: -0.0000

Data Index: 132918 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1165324 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1322730 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4258. Min Act: -0.0000

Data Index: 700903 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4196. Min Act: -0.0000

Data Index: 786834 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4009. Min Act: -0.0000

Data Index: 322979 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3956. Min Act: -0.0000

Data Index: 237620 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1129652 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4027. Min Act: -0.0000

Data Index: 711045 (C4 (Web Text))

Max Activating Token Index: 316