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

Dataset: The Pile

Neuron 304 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1131713 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0404. Min Act: 0.0000

Data Index: 1272555 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0396. Min Act: -0.0000

Data Index: 1876832 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1845430 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0386. Min Act: -0.0000

Data Index: 293650 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0379. Min Act: -0.0000

Data Index: 943437 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0377. Min Act: 0.0000

Data Index: 615477 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1457138 (The Pile)

Max Activating Token Index: 857

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1454322 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0371. Min Act: -0.0000

Data Index: 362399 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1023991 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0354. Min Act: 0.0000

Data Index: 935667 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0364. Min Act: -0.0000

Data Index: 1183114 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0366. Min Act: -0.0000

Data Index: 776384 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1620295 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0348. Min Act: -0.0000

Data Index: 741881 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0359. Min Act: 0.0000

Data Index: 47220 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0347. Min Act: -0.0000

Data Index: 4619 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1378400 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0355. Min Act: -0.0000

Data Index: 704012 (The Pile)

Max Activating Token Index: 449