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

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

Neuron 536 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1243055 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.7023. Min Act: -0.0000

Data Index: 893583 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.7029. Min Act: -0.0000

Data Index: 17287 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6963. Min Act: -0.0000

Data Index: 85812 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1273380 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6740. Min Act: -0.0000

Data Index: 633940 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6752. Min Act: -0.0000

Data Index: 368446 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1046462 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6672. Min Act: -0.0000

Data Index: 876930 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6453. Min Act: -0.0000

Data Index: 183601 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6343. Min Act: -0.0000

Data Index: 346527 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1145466 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6121. Min Act: -0.0000

Data Index: 544012 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6290. Min Act: -0.0000

Data Index: 409301 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6238. Min Act: -0.0000

Data Index: 840796 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6239. Min Act: -0.0000

Data Index: 878165 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6001. Min Act: -0.0000

Data Index: 142760 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6155. Min Act: -0.0000

Data Index: 73342 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1152191 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6323. Min Act: -0.0000

Data Index: 368847 (C4 (Web Text))

Max Activating Token Index: 76