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

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

Neuron 1235 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0002

Data Index: 319893 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1215434 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0455. Min Act: -0.0002

Data Index: 38781 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0407. Min Act: -0.0002

Data Index: 752936 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0376. Min Act: -0.0002

Data Index: 897759 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0360. Min Act: -0.0002

Data Index: 350077 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1201320 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0371. Min Act: -0.0002

Data Index: 629561 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1122746 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0351. Min Act: -0.0002

Data Index: 491509 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0379. Min Act: -0.0002

Data Index: 828508 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0357. Min Act: -0.0002

Data Index: 888550 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0348. Min Act: -0.0002

Data Index: 474184 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0339. Min Act: -0.0002

Data Index: 497476 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1264017 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0345. Min Act: -0.0002

Data Index: 605833 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0341. Min Act: -0.0002

Data Index: 550340 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0328. Min Act: -0.0002

Data Index: 675709 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1023785 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0326. Min Act: -0.0002

Data Index: 371076 (C4 (Web Text))

Max Activating Token Index: 831