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

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

Neuron 1342 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.8031. Min Act: -0.0000

Data Index: 801190 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7190. Min Act: -0.0000

Data Index: 650420 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7394. Min Act: -0.0000

Data Index: 821440 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1248243 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6082. Min Act: -0.0000

Data Index: 795691 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6719. Min Act: -0.0000

Data Index: 771119 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6907. Min Act: -0.0000

Data Index: 810608 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1147675 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6239. Min Act: -0.0000

Data Index: 845615 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6349. Min Act: -0.0000

Data Index: 802016 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1009296 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6194. Min Act: -0.0000

Data Index: 371047 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5482. Min Act: -0.0000

Data Index: 855925 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5720. Min Act: -0.0000

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5698. Min Act: -0.0000

Data Index: 621257 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5689. Min Act: -0.0000

Data Index: 233453 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5848. Min Act: -0.0000

Data Index: 965222 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5746. Min Act: -0.0000

Data Index: 640851 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1286668 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5387. Min Act: -0.0000

Data Index: 590017 (C4 (Web Text))

Max Activating Token Index: 1000