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

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

Neuron 4672 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1054089 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1183309 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0616. Min Act: -0.0003

Data Index: 807483 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0570. Min Act: -0.0003

Data Index: 364102 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0661. Min Act: -0.0003

Data Index: 131962 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0609. Min Act: -0.0002

Data Index: 226163 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1060618 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0616. Min Act: -0.0003

Data Index: 839323 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0563. Min Act: -0.0002

Data Index: 536817 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0511. Min Act: -0.0003

Data Index: 91138 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1296715 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1356133 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0527. Min Act: -0.0003

Data Index: 723266 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0565. Min Act: -0.0003

Data Index: 894984 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0511. Min Act: -0.0003

Data Index: 84207 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1091739 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0493. Min Act: -0.0003

Data Index: 730337 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0513. Min Act: -0.0003

Data Index: 328297 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0476. Min Act: -0.0003

Data Index: 736337 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1296071 (C4 (Web Text))

Max Activating Token Index: 28