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

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

Neuron 5045 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0000

Data Index: 584847 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0364. Min Act: -0.0000

Data Index: 142718 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1064904 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1457201 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0352. Min Act: -0.0000

Data Index: 165028 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1406618 (Python Code)

Max Activating Token Index: 814

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1588560 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1423548 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0324. Min Act: -0.0000

Data Index: 506929 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1588904 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0372. Min Act: -0.0000

Data Index: 783046 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1195235 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0336. Min Act: -0.0000

Data Index: 486111 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1419729 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0306. Min Act: -0.0000

Data Index: 622289 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1101187 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0324. Min Act: -0.0000

Data Index: 333767 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0311. Min Act: -0.0000

Data Index: 1585131 (Python Code)

Max Activating Token Index: 757

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0295. Min Act: -0.0000

Data Index: 712726 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0320. Min Act: -0.0000

Data Index: 256161 (C4 (Web Text))

Max Activating Token Index: 706