Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.8210. Min Act: -0.0000

Data Index: 26309 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6611. Min Act: -0.0000

Data Index: 709146 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6824. Min Act: -0.0000

Data Index: 721523 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6757. Min Act: -0.0000

Data Index: 91919 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6219. Min Act: -0.0000

Data Index: 325735 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6072. Min Act: -0.0000

Data Index: 447624 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5819. Min Act: -0.0000

Data Index: 545670 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5550. Min Act: -0.0000

Data Index: 987950 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5586. Min Act: -0.0000

Data Index: 276809 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5526. Min Act: -0.0000

Data Index: 654985 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5704. Min Act: -0.0000

Data Index: 61381 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5310. Min Act: -0.0000

Data Index: 994301 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5635. Min Act: -0.0000

Data Index: 194528 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5433. Min Act: -0.0000

Data Index: 136649 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5431. Min Act: -0.0000

Data Index: 503220 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1336733 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5396. Min Act: -0.0000

Data Index: 724157 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5524. Min Act: -0.0000

Data Index: 517878 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5328. Min Act: -0.0000

Data Index: 611566 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1131835 (C4 (Web Text))

Max Activating Token Index: 876