Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2000 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0005

Data Index: 582766 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0198. Min Act: -0.0005

Data Index: 51266 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1238192 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0189. Min Act: -0.0005

Data Index: 968050 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0192. Min Act: -0.0005

Data Index: 38237 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0186. Min Act: -0.0006

Data Index: 480835 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0183. Min Act: -0.0005

Data Index: 718209 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0173. Min Act: -0.0005

Data Index: 264673 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0175. Min Act: -0.0005

Data Index: 750815 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0175. Min Act: -0.0005

Data Index: 743241 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1049761 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0170. Min Act: -0.0005

Data Index: 199961 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0170. Min Act: -0.0005

Data Index: 1036180 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0169. Min Act: -0.0005

Data Index: 258853 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0168. Min Act: -0.0005

Data Index: 1230618 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0171. Min Act: -0.0005

Data Index: 168131 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0166. Min Act: -0.0006

Data Index: 674395 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0170. Min Act: -0.0005

Data Index: 877734 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0170. Min Act: -0.0006

Data Index: 998325 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0170. Min Act: -0.0005

Data Index: 90793 (C4 (Web Text))

Max Activating Token Index: 77