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

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

Neuron 2440 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: 0.6242. Min Range: -0.6242

Max Act: 0.5929. Min Act: -0.0001

Data Index: 126924 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.6242. Min Act: -0.0001

Data Index: 501846 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5542. Min Act: -0.0001

Data Index: 1194395 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.6141. Min Act: -0.0001

Data Index: 710682 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5488. Min Act: -0.0001

Data Index: 1005062 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5780. Min Act: -0.0001

Data Index: 1237276 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5446. Min Act: -0.0001

Data Index: 959119 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5627. Min Act: -0.0001

Data Index: 1357808 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5971. Min Act: -0.0001

Data Index: 1211349 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5482. Min Act: -0.0001

Data Index: 396427 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5486. Min Act: -0.0001

Data Index: 1122170 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5503. Min Act: -0.0001

Data Index: 852361 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5269. Min Act: -0.0001

Data Index: 1172603 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5284. Min Act: -0.0001

Data Index: 334275 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5361. Min Act: -0.0001

Data Index: 1110202 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5160. Min Act: -0.0001

Data Index: 1346031 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5155. Min Act: -0.0001

Data Index: 1262474 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.4982. Min Act: -0.0001

Data Index: 88145 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.5047. Min Act: -0.0001

Data Index: 913414 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.6242. Min Range: -0.6242

Max Act: 0.4919. Min Act: -0.0001

Data Index: 609602 (C4 (Web Text))

Max Activating Token Index: 765