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

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

Neuron 3228 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.7233. Min Act: -0.0000

Data Index: 615482 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.7128. Min Act: -0.0000

Data Index: 63970 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6250. Min Act: -0.0000

Data Index: 169391 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6357. Min Act: -0.0000

Data Index: 744818 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1279478 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1118331 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5968. Min Act: -0.0000

Data Index: 652665 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1119790 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5540. Min Act: -0.0000

Data Index: 345972 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5745. Min Act: -0.0000

Data Index: 299092 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5580. Min Act: -0.0000

Data Index: 873291 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1346371 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5632. Min Act: -0.0000

Data Index: 127781 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1249936 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1103901 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5300. Min Act: -0.0000

Data Index: 63436 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5248. Min Act: -0.0000

Data Index: 262180 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5285. Min Act: -0.0000

Data Index: 152832 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5037. Min Act: -0.0000

Data Index: 870241 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.4692. Min Act: -0.0000

Data Index: 271499 (C4 (Web Text))

Max Activating Token Index: 91