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

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

Neuron 3733 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.5201. Min Act: -0.0002

Data Index: 1058322 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4957. Min Act: -0.0002

Data Index: 1189632 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4762. Min Act: -0.0003

Data Index: 370475 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4750. Min Act: -0.0002

Data Index: 299213 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4186. Min Act: -0.0002

Data Index: 900502 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4078. Min Act: -0.0002

Data Index: 605248 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4332. Min Act: -0.0002

Data Index: 1273425 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4013. Min Act: -0.0002

Data Index: 1260993 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4202. Min Act: -0.0002

Data Index: 201484 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3999. Min Act: -0.0003

Data Index: 1216893 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3725. Min Act: -0.0002

Data Index: 339480 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3730. Min Act: -0.0002

Data Index: 1279116 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3651. Min Act: -0.0002

Data Index: 1079931 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3667. Min Act: -0.0002

Data Index: 247857 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3513. Min Act: -0.0002

Data Index: 44695 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3395. Min Act: -0.0003

Data Index: 122079 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3509. Min Act: -0.0002

Data Index: 1290353 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3537. Min Act: -0.0002

Data Index: 871288 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3289. Min Act: -0.0002

Data Index: 265953 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3281. Min Act: -0.0003

Data Index: 335670 (C4 (Web Text))

Max Activating Token Index: 498