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

Dataset: The Pile

Neuron 3250 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: 0.5640. Min Range: -0.5640

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1897185 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4883. Min Act: -0.0000

Data Index: 394111 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1772457 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4883. Min Act: -0.0000

Data Index: 985833 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1389250 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1955218 (The Pile)

Max Activating Token Index: 503

Text #6

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1835006 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4446. Min Act: -0.0000

Data Index: 278989 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4719. Min Act: -0.0000

Data Index: 89617 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4427. Min Act: -0.0000

Data Index: 309642 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4378. Min Act: -0.0000

Data Index: 675776 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1510264 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1860850 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4172. Min Act: -0.0000

Data Index: 662649 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4238. Min Act: -0.0000

Data Index: 131930 (The Pile)

Max Activating Token Index: 878

Text #15

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4320. Min Act: -0.0000

Data Index: 34758 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1509560 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4195. Min Act: -0.0000

Data Index: 892144 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1968507 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.5640. Min Range: -0.5640

Max Act: 0.4049. Min Act: -0.0000

Data Index: 291152 (The Pile)

Max Activating Token Index: 150