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

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

Neuron 1721 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1322817 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1180526 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0524. Min Act: -0.0001

Data Index: 570612 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0518. Min Act: -0.0001

Data Index: 230188 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0505. Min Act: -0.0001

Data Index: 563043 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0472. Min Act: -0.0001

Data Index: 27656 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1381738 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1222043 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0429. Min Act: -0.0001

Data Index: 340685 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1513125 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0381. Min Act: -0.0001

Data Index: 929430 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0379. Min Act: -0.0001

Data Index: 252773 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1158523 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0402. Min Act: -0.0001

Data Index: 554163 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1395724 (Python Code)

Max Activating Token Index: 607

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0361. Min Act: -0.0001

Data Index: 262497 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0411. Min Act: -0.0001

Data Index: 240477 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1535067 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0380. Min Act: -0.0001

Data Index: 528830 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0380. Min Act: -0.0001

Data Index: 588108 (C4 (Web Text))

Max Activating Token Index: 695