Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1558 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6359. Min Act: -0.0000

Data Index: 780247 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4795. Min Act: -0.0000

Data Index: 171066 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5114. Min Act: -0.0000

Data Index: 803515 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1052627 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5097. Min Act: -0.0000

Data Index: 898303 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1359283 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4556. Min Act: -0.0000

Data Index: 736705 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4729. Min Act: -0.0000

Data Index: 538864 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1883342 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1648121 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1701591 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1984555 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4445. Min Act: -0.0000

Data Index: 395926 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4225. Min Act: -0.0000

Data Index: 669705 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4461. Min Act: -0.0000

Data Index: 665439 (The Pile)

Max Activating Token Index: 156

Text #15

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1852755 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4388. Min Act: -0.0000

Data Index: 131856 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4363. Min Act: -0.0000

Data Index: 663492 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4604. Min Act: -0.0000

Data Index: 836081 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4290. Min Act: -0.0000

Data Index: 314382 (The Pile)

Max Activating Token Index: 410