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

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

Neuron 2344 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1543223 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1545759 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0352. Min Act: -0.0003

Data Index: 397444 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0366. Min Act: -0.0003

Data Index: 783739 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0332. Min Act: -0.0002

Data Index: 867471 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0330. Min Act: -0.0003

Data Index: 116410 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0317. Min Act: -0.0002

Data Index: 144738 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1499406 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0300. Min Act: -0.0003

Data Index: 437754 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1451741 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0289. Min Act: -0.0003

Data Index: 352605 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0268. Min Act: -0.0003

Data Index: 385902 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1249109 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1392137 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0280. Min Act: -0.0003

Data Index: 241190 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0275. Min Act: -0.0002

Data Index: 228633 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0268. Min Act: -0.0003

Data Index: 14215 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0271. Min Act: -0.0003

Data Index: 737366 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0269. Min Act: -0.0002

Data Index: 379843 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1329716 (C4 (Web Text))

Max Activating Token Index: 463