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

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

Neuron 4107 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1040118 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1903. Min Act: -0.0000

Data Index: 230501 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1444. Min Act: -0.0000

Data Index: 188620 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1236. Min Act: -0.0000

Data Index: 267708 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1555970 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0369. Min Act: -0.0000

Data Index: 1224271 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1826. Min Act: -0.0000

Data Index: 414568 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.1061. Min Act: -0.0000

Data Index: 691684 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1570496 (Python Code)

Max Activating Token Index: 322

Text #9

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1447136 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 1.3192. Min Range: -1.3192

Max Act: 0.9485. Min Act: -0.0000

Data Index: 299285 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0584. Min Act: -0.0000

Data Index: 473589 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 1.3192. Min Range: -1.3192

Max Act: 0.9929. Min Act: -0.0000

Data Index: 977646 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 1.3192. Min Range: -1.3192

Max Act: 0.9870. Min Act: -0.0000

Data Index: 559454 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0412. Min Act: -0.0000

Data Index: 348188 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1164436 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0606. Min Act: -0.0000

Data Index: 719335 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 1.3192. Min Range: -1.3192

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1486755 (Python Code)

Max Activating Token Index: 99

Text #18

Max Range: 1.3192. Min Range: -1.3192

Max Act: 0.9543. Min Act: -0.0000

Data Index: 578201 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.3192. Min Range: -1.3192

Max Act: 1.0162. Min Act: -0.0000

Data Index: 207473 (C4 (Web Text))

Max Activating Token Index: 998