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

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

Neuron 1924 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.5494. Min Act: -0.0003

Data Index: 489873 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3102. Min Act: -0.0003

Data Index: 41819 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4669. Min Act: -0.0003

Data Index: 148546 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.6207. Min Act: -0.0003

Data Index: 446610 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4349. Min Act: -0.0004

Data Index: 787634 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.2722. Min Act: -0.0004

Data Index: 144531 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3913. Min Act: -0.0003

Data Index: 555521 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4575. Min Act: -0.0003

Data Index: 539906 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3156. Min Act: -0.0004

Data Index: 1252502 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3382. Min Act: -0.0003

Data Index: 1189514 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.1687. Min Act: -0.0003

Data Index: 37589 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3201. Min Act: -0.0003

Data Index: 978046 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3132. Min Act: -0.0003

Data Index: 319359 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4020. Min Act: -0.0003

Data Index: 1133727 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3292. Min Act: -0.0003

Data Index: 217334 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.1900. Min Act: -0.0003

Data Index: 510946 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3193. Min Act: -0.0003

Data Index: 973312 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.2677. Min Act: -0.0003

Data Index: 1173393 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.2015. Min Act: -0.0003

Data Index: 691552 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.2231. Min Act: -0.0003

Data Index: 1206312 (C4 (Web Text))

Max Activating Token Index: 103