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

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

Neuron 3776 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: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1140451 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0316. Min Act: -0.0002

Data Index: 192284 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1043487 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0306. Min Act: -0.0002

Data Index: 756797 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0301. Min Act: -0.0002

Data Index: 547429 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0301. Min Act: -0.0002

Data Index: 706473 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0291. Min Act: -0.0002

Data Index: 312572 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0297. Min Act: -0.0002

Data Index: 858502 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0296. Min Act: -0.0002

Data Index: 397304 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0289. Min Act: -0.0002

Data Index: 720410 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0295. Min Act: -0.0002

Data Index: 832223 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0289. Min Act: -0.0002

Data Index: 193556 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0297. Min Act: -0.0002

Data Index: 156168 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1155735 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0285. Min Act: -0.0002

Data Index: 760104 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0289. Min Act: -0.0002

Data Index: 761295 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1427906 (Python Code)

Max Activating Token Index: 803

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0281. Min Act: -0.0002

Data Index: 293293 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0287. Min Act: -0.0002

Data Index: 106762 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0281. Min Act: -0.0002

Data Index: 810905 (C4 (Web Text))

Max Activating Token Index: 105