Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3131 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1728. Min Act: -0.0002

Data Index: 65064 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1545. Min Act: -0.0002

Data Index: 391814 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1228. Min Act: -0.0002

Data Index: 34574 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1259. Min Act: -0.0002

Data Index: 851210 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1334. Min Act: -0.0002

Data Index: 1353837 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1184. Min Act: -0.0002

Data Index: 747653 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1295445 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1164. Min Act: -0.0002

Data Index: 944583 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1210041 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0917. Min Act: -0.0002

Data Index: 202817 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1357152 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1113. Min Act: -0.0002

Data Index: 307159 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1086. Min Act: -0.0002

Data Index: 715141 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1008004 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0949. Min Act: -0.0002

Data Index: 14317 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0947. Min Act: -0.0002

Data Index: 217018 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0994. Min Act: -0.0002

Data Index: 991370 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0899. Min Act: -0.0002

Data Index: 501911 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1061. Min Act: -0.0002

Data Index: 522192 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0974. Min Act: -0.0002

Data Index: 523514 (C4 (Web Text))

Max Activating Token Index: 775