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

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

Neuron 522 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: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0003

Data Index: 995155 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0330. Min Act: -0.0003

Data Index: 208955 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0352. Min Act: -0.0003

Data Index: 677052 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1213599 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1022233 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1492281 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0299. Min Act: -0.0003

Data Index: 319759 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0273. Min Act: -0.0003

Data Index: 453427 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1323070 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1309421 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0239. Min Act: -0.0003

Data Index: 51887 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0256. Min Act: -0.0003

Data Index: 114707 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0297. Min Act: -0.0003

Data Index: 792118 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1205631 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0251. Min Act: -0.0003

Data Index: 692282 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1274810 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1063087 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0221. Min Act: -0.0003

Data Index: 384938 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1303822 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0233. Min Act: -0.0003

Data Index: 656023 (C4 (Web Text))

Max Activating Token Index: 822