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

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

Neuron 1217 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: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1294305 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0527. Min Act: -0.0000

Data Index: 428818 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0443. Min Act: -0.0000

Data Index: 486970 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1531018 (Python Code)

Max Activating Token Index: 873

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0447. Min Act: -0.0000

Data Index: 818437 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0428. Min Act: -0.0000

Data Index: 430019 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1141291 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1377410 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0378. Min Act: -0.0000

Data Index: 412986 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0378. Min Act: -0.0000

Data Index: 219355 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0389. Min Act: -0.0000

Data Index: 608027 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0386. Min Act: -0.0000

Data Index: 176687 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0398. Min Act: -0.0000

Data Index: 1649331 (Python Code)

Max Activating Token Index: 692

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0381. Min Act: -0.0000

Data Index: 493014 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0396. Min Act: -0.0000

Data Index: 1601603 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0394. Min Act: -0.0000

Data Index: 66860 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0388. Min Act: -0.0000

Data Index: 232139 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1242586 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1112438 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1516143 (Python Code)

Max Activating Token Index: 659