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

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

Neuron 3127 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.5219. Min Act: -0.0002

Data Index: 1079923 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.5209. Min Act: -0.0003

Data Index: 1296102 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.4083. Min Act: -0.0003

Data Index: 46618 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3655. Min Act: -0.0002

Data Index: 615163 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3480. Min Act: -0.0003

Data Index: 294399 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3416. Min Act: -0.0003

Data Index: 561612 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3493. Min Act: -0.0003

Data Index: 361638 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3177. Min Act: -0.0003

Data Index: 189792 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3243. Min Act: -0.0003

Data Index: 1238790 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3213. Min Act: -0.0003

Data Index: 1299009 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3325. Min Act: -0.0003

Data Index: 1358950 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3004. Min Act: -0.0002

Data Index: 119231 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3082. Min Act: -0.0003

Data Index: 900306 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3068. Min Act: -0.0002

Data Index: 1044335 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3027. Min Act: -0.0003

Data Index: 229879 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3000. Min Act: -0.0003

Data Index: 338336 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.3087. Min Act: -0.0003

Data Index: 1164746 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.2841. Min Act: -0.0002

Data Index: 559830 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.2741. Min Act: -0.0003

Data Index: 1103134 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.5219. Min Range: -0.5219

Max Act: 0.2840. Min Act: -0.0002

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 1017