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

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

Neuron 3314 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8156. Min Range: -3.8156

Max Act: 3.8156. Min Act: -0.0000

Data Index: 672370 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 3.8156. Min Range: -3.8156

Max Act: 3.7910. Min Act: -0.0000

Data Index: 309885 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 3.8156. Min Range: -3.8156

Max Act: 3.6312. Min Act: -0.0000

Data Index: 1131177 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 3.8156. Min Range: -3.8156

Max Act: 3.3449. Min Act: -0.0000

Data Index: 276979 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 3.8156. Min Range: -3.8156

Max Act: 3.4896. Min Act: -0.0000

Data Index: 731461 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.6318. Min Act: -0.0000

Data Index: 806204 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.6359. Min Act: -0.0000

Data Index: 917073 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.3763. Min Act: -0.0000

Data Index: 1085061 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.2757. Min Act: -0.0000

Data Index: 476905 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.2168. Min Act: -0.0000

Data Index: 971203 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.1779. Min Act: 0.0000

Data Index: 124763 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.1498. Min Act: -0.0000

Data Index: 133151 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.1447. Min Act: -0.0000

Data Index: 605631 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.1056. Min Act: -0.0000

Data Index: 749758 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.8156. Min Range: -3.8156

Max Act: 2.1692. Min Act: -0.0000

Data Index: 953527 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.8156. Min Range: -3.8156

Max Act: 1.8112. Min Act: -0.0000

Data Index: 356579 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 3.8156. Min Range: -3.8156

Max Act: 1.9027. Min Act: -0.0000

Data Index: 854511 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 3.8156. Min Range: -3.8156

Max Act: 1.8770. Min Act: -0.0000

Data Index: 585668 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 3.8156. Min Range: -3.8156

Max Act: 1.8772. Min Act: -0.0000

Data Index: 148034 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 3.8156. Min Range: -3.8156

Max Act: 1.8645. Min Act: -0.0000

Data Index: 803189 (C4 (Web Text))

Max Activating Token Index: 225