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

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

Neuron 2702 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: 1.9269. Min Range: -1.9269

Max Act: 1.9269. Min Act: -0.0001

Data Index: 1048020 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.2264. Min Act: -0.0000

Data Index: 71291 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.3025. Min Act: -0.0000

Data Index: 169437 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.1823. Min Act: -0.0001

Data Index: 396456 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1223715 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.1311. Min Act: -0.0000

Data Index: 163830 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.1394. Min Act: -0.0000

Data Index: 35984 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.1202. Min Act: -0.0000

Data Index: 362885 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.1395. Min Act: -0.0000

Data Index: 299650 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.0893. Min Act: -0.0000

Data Index: 478198 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.1059. Min Act: -0.0000

Data Index: 268442 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.0503. Min Act: -0.0001

Data Index: 383726 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.0923. Min Act: -0.0001

Data Index: 1343250 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.0170. Min Act: -0.0000

Data Index: 16466 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.9269. Min Range: -1.9269

Max Act: 0.9166. Min Act: -0.0000

Data Index: 797139 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.9269. Min Range: -1.9269

Max Act: 0.9845. Min Act: -0.0001

Data Index: 1214132 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1023612 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.0008. Min Act: -0.0000

Data Index: 246634 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.9269. Min Range: -1.9269

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1143222 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.9269. Min Range: -1.9269

Max Act: 0.9597. Min Act: -0.0001

Data Index: 25885 (C4 (Web Text))

Max Activating Token Index: 755