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

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

Neuron 2577 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0001

Data Index: 742859 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1247955 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0395. Min Act: -0.0001

Data Index: 474604 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1151014 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0391. Min Act: -0.0001

Data Index: 335485 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0386. Min Act: -0.0001

Data Index: 941488 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0386. Min Act: -0.0001

Data Index: 172569 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0372. Min Act: -0.0001

Data Index: 98511 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0414. Min Act: -0.0001

Data Index: 618350 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1192053 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0326. Min Act: -0.0001

Data Index: 15581 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0348. Min Act: -0.0001

Data Index: 279973 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0278. Min Act: -0.0001

Data Index: 86902 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0333. Min Act: -0.0001

Data Index: 126847 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0323. Min Act: -0.0001

Data Index: 575028 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1197305 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0329. Min Act: -0.0001

Data Index: 934029 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0297. Min Act: -0.0001

Data Index: 945980 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0322. Min Act: -0.0001

Data Index: 325434 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1092524 (C4 (Web Text))

Max Activating Token Index: 27