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

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

Neuron 1164 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: 1.9036. Min Range: -1.9036

Max Act: 1.8715. Min Act: -0.0002

Data Index: 1113299 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.9036. Min Act: -0.0002

Data Index: 94093 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.5485. Min Act: -0.0002

Data Index: 361417 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.6080. Min Act: -0.0002

Data Index: 1283447 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.5189. Min Act: -0.0002

Data Index: 1353294 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.5495. Min Act: -0.0002

Data Index: 120900 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.6226. Min Act: -0.0002

Data Index: 800154 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.4129. Min Act: -0.0002

Data Index: 719857 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.4578. Min Act: -0.0002

Data Index: 1267081 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.6285. Min Act: -0.0002

Data Index: 283112 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.4717. Min Act: -0.0002

Data Index: 934582 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.4154. Min Act: -0.0002

Data Index: 816978 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.5058. Min Act: -0.0002

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.4541. Min Act: -0.0002

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.3837. Min Act: -0.0002

Data Index: 896511 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.3740. Min Act: -0.0002

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.3235. Min Act: -0.0002

Data Index: 622190 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.3911. Min Act: -0.0002

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.4359. Min Act: -0.0002

Data Index: 268210 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.9036. Min Range: -1.9036

Max Act: 1.3119. Min Act: -0.0002

Data Index: 1150808 (C4 (Web Text))

Max Activating Token Index: 169