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

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

Neuron 1628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1072200 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4477. Min Act: -0.0000

Data Index: 448679 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4316. Min Act: -0.0000

Data Index: 450578 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4260. Min Act: -0.0000

Data Index: 307375 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3997. Min Act: -0.0000

Data Index: 296699 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1313475 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3843. Min Act: -0.0001

Data Index: 214974 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3706. Min Act: -0.0000

Data Index: 685371 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3701. Min Act: -0.0000

Data Index: 408627 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1004789 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3434. Min Act: -0.0000

Data Index: 478870 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3394. Min Act: -0.0000

Data Index: 606154 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3498. Min Act: -0.0000

Data Index: 349971 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3486. Min Act: -0.0000

Data Index: 340695 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1327291 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3459. Min Act: -0.0000

Data Index: 150363 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3457. Min Act: -0.0000

Data Index: 474623 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3156. Min Act: -0.0000

Data Index: 355469 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3450. Min Act: -0.0000

Data Index: 257673 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3334. Min Act: -0.0000

Data Index: 89842 (C4 (Web Text))

Max Activating Token Index: 535