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

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

Neuron 3515 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.7524. Min Act: -0.0002

Data Index: 73554 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.7091. Min Act: -0.0002

Data Index: 848059 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.5248. Min Act: -0.0002

Data Index: 198059 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.7105. Min Act: -0.0002

Data Index: 46355 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.6762. Min Act: -0.0002

Data Index: 955446 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.7704. Min Act: -0.0002

Data Index: 565483 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.5980. Min Act: -0.0002

Data Index: 344763 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.6760. Min Act: -0.0002

Data Index: 990063 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.5681. Min Act: -0.0002

Data Index: 505955 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.6137. Min Act: -0.0002

Data Index: 203645 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.6490. Min Act: -0.0002

Data Index: 562452 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.5657. Min Act: -0.0002

Data Index: 512062 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.8215. Min Act: -0.0002

Data Index: 1334084 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.6031. Min Act: -0.0001

Data Index: 612690 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.5355. Min Act: -0.0002

Data Index: 283133 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.5863. Min Act: -0.0002

Data Index: 1149075 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.5549. Min Act: -0.0002

Data Index: 918960 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.6677. Min Act: -0.0001

Data Index: 570255 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.5559. Min Act: -0.0001

Data Index: 1027768 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 1.8215. Min Range: -1.8215

Max Act: 1.4563. Min Act: -0.0001

Data Index: 342809 (C4 (Web Text))

Max Activating Token Index: 328