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

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

Neuron 3052 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0001

Data Index: 994512 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0245. Min Act: -0.0002

Data Index: 738920 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1200700 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1195773 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0186. Min Act: -0.0002

Data Index: 173648 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0261. Min Act: -0.0002

Data Index: 891633 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0211. Min Act: -0.0001

Data Index: 551628 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0238. Min Act: -0.0001

Data Index: 546040 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0261. Min Act: -0.0001

Data Index: 667033 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1263465 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0205. Min Act: -0.0002

Data Index: 389364 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0201. Min Act: -0.0002

Data Index: 329491 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1066306 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1227890 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0222. Min Act: -0.0002

Data Index: 145657 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0187. Min Act: -0.0002

Data Index: 128023 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0212. Min Act: -0.0001

Data Index: 198235 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0187. Min Act: -0.0002

Data Index: 746997 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1349808 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0182. Min Act: -0.0002

Data Index: 627596 (C4 (Web Text))

Max Activating Token Index: 795