Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0283. Min Act: -0.0002

Data Index: 109938 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0273. Min Act: -0.0002

Data Index: 413737 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1179866 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1655789 (Python Code)

Max Activating Token Index: 840

Text #4

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0216. Min Act: -0.0002

Data Index: 543728 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0215. Min Act: -0.0002

Data Index: 896279 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1150813 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1011894 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1397595 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1049630 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1434054 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1580088 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0193. Min Act: -0.0002

Data Index: 175062 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1117716 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1103287 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0185. Min Act: -0.0002

Data Index: 824747 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1071414 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1531784 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0181. Min Act: -0.0002

Data Index: 802585 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1002991 (C4 (Web Text))

Max Activating Token Index: 630