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

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

Neuron 3437 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0440. Min Range: -1.0440

Max Act: 1.0440. Min Act: -0.0001

Data Index: 1227437 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8740. Min Act: -0.0001

Data Index: 149140 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1080139 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7501. Min Act: -0.0001

Data Index: 109233 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7602. Min Act: -0.0001

Data Index: 1226698 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7448. Min Act: -0.0001

Data Index: 1024493 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7367. Min Act: -0.0001

Data Index: 204642 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7391. Min Act: -0.0001

Data Index: 11326 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8477. Min Act: -0.0001

Data Index: 447452 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7382. Min Act: -0.0001

Data Index: 217203 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6893. Min Act: -0.0001

Data Index: 818274 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1061831 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7244. Min Act: -0.0001

Data Index: 432196 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6993. Min Act: -0.0001

Data Index: 505337 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6992. Min Act: -0.0001

Data Index: 1218778 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6718. Min Act: -0.0001

Data Index: 815020 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6960. Min Act: -0.0001

Data Index: 1359719 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7113. Min Act: -0.0001

Data Index: 692222 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6380. Min Act: -0.0001

Data Index: 362425 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6394. Min Act: -0.0001

Data Index: 1201810 (C4 (Web Text))

Max Activating Token Index: 577