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

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

Neuron 4656 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4511. Min Act: -0.0002

Data Index: 795746 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4271. Min Act: -0.0002

Data Index: 1102903 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4628. Min Act: -0.0002

Data Index: 419579 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4408. Min Act: -0.0002

Data Index: 1357914 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4095. Min Act: -0.0002

Data Index: 70600 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4086. Min Act: -0.0002

Data Index: 1200393 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4030. Min Act: -0.0002

Data Index: 666329 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4392. Min Act: -0.0002

Data Index: 520936 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3765. Min Act: -0.0002

Data Index: 458765 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3983. Min Act: -0.0002

Data Index: 497764 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3354. Min Act: -0.0002

Data Index: 327369 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3808. Min Act: -0.0002

Data Index: 21070 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3908. Min Act: -0.0002

Data Index: 997014 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3867. Min Act: -0.0002

Data Index: 250228 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.4157. Min Act: -0.0002

Data Index: 161976 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3970. Min Act: -0.0002

Data Index: 769764 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3629. Min Act: -0.0002

Data Index: 788312 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3596. Min Act: -0.0002

Data Index: 55017 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3455. Min Act: -0.0002

Data Index: 973087 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.4628. Min Range: -0.4628

Max Act: 0.3836. Min Act: -0.0002

Data Index: 33230 (C4 (Web Text))

Max Activating Token Index: 230