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

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

Neuron 3784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.7237. Min Act: -0.0001

Data Index: 922619 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5842. Min Act: -0.0001

Data Index: 728185 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.5401. Min Act: -0.0001

Data Index: 691363 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4859. Min Act: -0.0001

Data Index: 760245 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4908. Min Act: -0.0001

Data Index: 803710 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4842. Min Act: -0.0001

Data Index: 1310447 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4728. Min Act: -0.0000

Data Index: 42760 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4667. Min Act: -0.0001

Data Index: 299445 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4731. Min Act: -0.0001

Data Index: 1214079 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1105345 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4455. Min Act: -0.0001

Data Index: 163767 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4150. Min Act: -0.0001

Data Index: 447432 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4445. Min Act: -0.0001

Data Index: 107581 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4222. Min Act: -0.0001

Data Index: 1351447 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.3576. Min Act: -0.0001

Data Index: 499309 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4207. Min Act: -0.0001

Data Index: 58214 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.4016. Min Act: -0.0000

Data Index: 790395 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.3906. Min Act: -0.0001

Data Index: 938309 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.3949. Min Act: -0.0001

Data Index: 191258 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.7237. Min Range: -0.7237

Max Act: 0.3982. Min Act: -0.0001

Data Index: 660303 (C4 (Web Text))

Max Activating Token Index: 108