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

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

Neuron 3666 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.2164. Min Act: -0.0002

Data Index: 760335 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.2318. Min Act: -0.0001

Data Index: 935023 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1774. Min Act: -0.0001

Data Index: 1142377 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1982. Min Act: -0.0001

Data Index: 946996 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1809. Min Act: -0.0002

Data Index: 642442 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1870. Min Act: -0.0002

Data Index: 280364 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1535. Min Act: -0.0002

Data Index: 182360 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1625. Min Act: -0.0002

Data Index: 174542 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.0558. Min Act: -0.0001

Data Index: 782320 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1473. Min Act: -0.0002

Data Index: 421287 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1255. Min Act: -0.0001

Data Index: 533238 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.0287. Min Act: -0.0002

Data Index: 531281 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 1.2318. Min Range: -1.2318

Max Act: 0.9805. Min Act: -0.0001

Data Index: 25940 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1324. Min Act: -0.0001

Data Index: 1197559 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.0488. Min Act: -0.0002

Data Index: 362912 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.0662. Min Act: -0.0002

Data Index: 149188 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.0113. Min Act: -0.0001

Data Index: 984137 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.0448. Min Act: -0.0002

Data Index: 698186 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.2318. Min Range: -1.2318

Max Act: 0.9596. Min Act: -0.0001

Data Index: 860129 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 1.2318. Min Range: -1.2318

Max Act: 1.1353. Min Act: -0.0002

Data Index: 56453 (C4 (Web Text))

Max Activating Token Index: 139