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

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

Neuron 99 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1120473 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0373. Min Act: -0.0000

Data Index: 309619 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0000

Data Index: 93840 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0355. Min Act: -0.0001

Data Index: 798157 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0378. Min Act: -0.0001

Data Index: 692506 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1066604 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0374. Min Act: -0.0000

Data Index: 855829 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0398. Min Act: -0.0000

Data Index: 1297559 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1529751 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0337. Min Act: -0.0000

Data Index: 900093 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1037465 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1283535 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0338. Min Act: -0.0000

Data Index: 177628 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0319. Min Act: -0.0000

Data Index: 1035643 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1241732 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1243963 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0301. Min Act: -0.0000

Data Index: 855112 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1391913 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0335. Min Act: -0.0000

Data Index: 291512 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0317. Min Act: -0.0000

Data Index: 86882 (C4 (Web Text))

Max Activating Token Index: 4