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

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

Neuron 176 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.7043. Min Act: -0.0001

Data Index: 833893 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.7130. Min Act: -0.0001

Data Index: 150781 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6700. Min Act: -0.0001

Data Index: 866882 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6415. Min Act: -0.0001

Data Index: 199318 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6163. Min Act: -0.0001

Data Index: 348121 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6354. Min Act: -0.0001

Data Index: 1217131 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6627. Min Act: -0.0001

Data Index: 1227994 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6825. Min Act: -0.0001

Data Index: 805770 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6606. Min Act: -0.0001

Data Index: 387038 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6396. Min Act: -0.0001

Data Index: 11380 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6774. Min Act: -0.0001

Data Index: 12261 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6527. Min Act: -0.0001

Data Index: 1334308 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6508. Min Act: -0.0001

Data Index: 917674 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5831. Min Act: -0.0001

Data Index: 930494 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6051. Min Act: -0.0001

Data Index: 111732 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6423. Min Act: -0.0001

Data Index: 376680 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1164238 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6278. Min Act: -0.0001

Data Index: 305951 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1204790 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6190. Min Act: -0.0001

Data Index: 50522 (C4 (Web Text))

Max Activating Token Index: 271