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

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

Neuron 1623 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.1154. Min Act: -0.0001

Data Index: 403254 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0875. Min Act: -0.0001

Data Index: 548676 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.1154. Min Range: -1.1154

Max Act: 1.0420. Min Act: -0.0001

Data Index: 1113376 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9831. Min Act: -0.0001

Data Index: 956907 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9132. Min Act: -0.0001

Data Index: 429598 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9185. Min Act: -0.0001

Data Index: 977201 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8816. Min Act: -0.0001

Data Index: 896209 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8859. Min Act: -0.0001

Data Index: 72236 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.9106. Min Act: -0.0001

Data Index: 877600 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8848. Min Act: -0.0001

Data Index: 1012055 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8894. Min Act: -0.0001

Data Index: 92076 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8411. Min Act: -0.0001

Data Index: 1243157 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8858. Min Act: -0.0001

Data Index: 408007 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8868. Min Act: -0.0001

Data Index: 903595 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8428. Min Act: -0.0001

Data Index: 432443 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.7893. Min Act: -0.0001

Data Index: 4104 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.7866. Min Act: -0.0001

Data Index: 740194 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8348. Min Act: -0.0001

Data Index: 134154 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8361. Min Act: -0.0001

Data Index: 1123061 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.1154. Min Range: -1.1154

Max Act: 0.8170. Min Act: -0.0001

Data Index: 798815 (C4 (Web Text))

Max Activating Token Index: 543