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

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

Neuron 3855 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0002

Data Index: 73068 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1076368 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1002554 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0329. Min Act: -0.0002

Data Index: 570119 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0321. Min Act: -0.0002

Data Index: 686512 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1207078 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0322. Min Act: -0.0002

Data Index: 337832 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0316. Min Act: -0.0002

Data Index: 261200 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0306. Min Act: -0.0002

Data Index: 681255 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0299. Min Act: -0.0002

Data Index: 46010 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0303. Min Act: -0.0002

Data Index: 923970 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0302. Min Act: -0.0002

Data Index: 467963 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0302. Min Act: -0.0002

Data Index: 504758 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1212513 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0300. Min Act: -0.0002

Data Index: 769774 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0300. Min Act: -0.0002

Data Index: 146361 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0297. Min Act: -0.0002

Data Index: 498880 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0296. Min Act: -0.0002

Data Index: 188218 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0291. Min Act: -0.0002

Data Index: 4056 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0296. Min Act: -0.0002

Data Index: 514419 (C4 (Web Text))

Max Activating Token Index: 725