Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 484 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0002

Data Index: 36199 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1111221 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1164. Min Act: -0.0002

Data Index: 418437 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1159. Min Act: -0.0002

Data Index: 746366 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1185. Min Act: -0.0002

Data Index: 192304 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1111. Min Act: -0.0002

Data Index: 314128 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1046. Min Act: -0.0002

Data Index: 366157 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1080. Min Act: -0.0002

Data Index: 581617 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1113. Min Act: -0.0002

Data Index: 159211 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1033. Min Act: -0.0002

Data Index: 724745 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1033965 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0992. Min Act: -0.0002

Data Index: 677987 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1011. Min Act: -0.0002

Data Index: 476654 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1049. Min Act: -0.0002

Data Index: 468874 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1145423 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1007. Min Act: -0.0002

Data Index: 438455 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1002. Min Act: -0.0002

Data Index: 262447 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1038. Min Act: -0.0002

Data Index: 872325 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0986. Min Act: -0.0002

Data Index: 959675 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1026. Min Act: -0.0002

Data Index: 82517 (C4 (Web Text))

Max Activating Token Index: 873