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

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

Neuron 4836 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.8790. Min Act: -0.0002

Data Index: 737111 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.9189. Min Act: -0.0003

Data Index: 715892 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.8469. Min Act: -0.0002

Data Index: 1073067 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.7463. Min Act: -0.0002

Data Index: 712462 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.8754. Min Act: -0.0002

Data Index: 790805 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.7669. Min Act: -0.0002

Data Index: 700016 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.7055. Min Act: -0.0002

Data Index: 45535 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.7196. Min Act: -0.0002

Data Index: 1323239 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.7310. Min Act: -0.0002

Data Index: 1081832 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6853. Min Act: -0.0002

Data Index: 246558 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6531. Min Act: -0.0002

Data Index: 255684 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6669. Min Act: -0.0002

Data Index: 1357625 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.7283. Min Act: -0.0002

Data Index: 1076952 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6680. Min Act: -0.0002

Data Index: 1191990 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6222. Min Act: -0.0002

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6368. Min Act: -0.0002

Data Index: 966172 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6580. Min Act: -0.0002

Data Index: 704302 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6629. Min Act: -0.0002

Data Index: 878225 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.6304. Min Act: -0.0002

Data Index: 143173 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 2.9189. Min Range: -2.9189

Max Act: 2.5786. Min Act: -0.0002

Data Index: 999437 (C4 (Web Text))

Max Activating Token Index: 390