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

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

Neuron 4497 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6793. Min Act: -0.0000

Data Index: 90527 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6280. Min Act: -0.0000

Data Index: 505384 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5806. Min Act: -0.0000

Data Index: 389383 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1177273 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3485. Min Act: -0.0000

Data Index: 972821 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3787. Min Act: -0.0000

Data Index: 852341 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3077. Min Act: -0.0000

Data Index: 811001 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1221441 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3359. Min Act: -0.0000

Data Index: 439196 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3288. Min Act: -0.0000

Data Index: 267035 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3092. Min Act: -0.0000

Data Index: 892564 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1262676 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3328. Min Act: -0.0000

Data Index: 352220 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1280157 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1266683 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.2728. Min Act: -0.0000

Data Index: 817997 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1145825 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.2682. Min Act: -0.0000

Data Index: 295224 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.2519. Min Act: -0.0000

Data Index: 107491 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.2557. Min Act: -0.0000

Data Index: 576698 (C4 (Web Text))

Max Activating Token Index: 892