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

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

Neuron 1403 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.8322. Min Act: -0.0001

Data Index: 341639 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.2665. Min Act: -0.0001

Data Index: 369294 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.2541. Min Act: -0.0001

Data Index: 99046 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.1316. Min Act: -0.0001

Data Index: 759882 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.2554. Min Act: -0.0001

Data Index: 1292219 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.2226. Min Act: -0.0001

Data Index: 126593 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.1486. Min Act: -0.0001

Data Index: 809637 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.1643. Min Act: -0.0001

Data Index: 702564 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.1664. Min Act: -0.0001

Data Index: 244902 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.1116. Min Act: -0.0001

Data Index: 195072 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.0948. Min Act: -0.0001

Data Index: 374046 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.1334. Min Act: -0.0001

Data Index: 432993 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.0414. Min Act: -0.0001

Data Index: 1171650 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.0677. Min Act: -0.0001

Data Index: 527318 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.0075. Min Act: -0.0001

Data Index: 1000841 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 1.8322. Min Range: -1.8322

Max Act: 0.9801. Min Act: -0.0001

Data Index: 452748 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.0048. Min Act: -0.0001

Data Index: 1059653 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.8322. Min Range: -1.8322

Max Act: 0.9738. Min Act: -0.0001

Data Index: 1086883 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 1.8322. Min Range: -1.8322

Max Act: 0.9723. Min Act: -0.0001

Data Index: 928545 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.8322. Min Range: -1.8322

Max Act: 1.0097. Min Act: -0.0001

Data Index: 1197375 (C4 (Web Text))

Max Activating Token Index: 576