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

Dataset: The Pile

Neuron 1254 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1336525 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1275917 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8106. Min Act: -0.0000

Data Index: 426770 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1424409 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7593. Min Act: -0.0000

Data Index: 955016 (The Pile)

Max Activating Token Index: 81

Text #5

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7227. Min Act: -0.0000

Data Index: 287855 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1879075 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1683354 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7160. Min Act: -0.0000

Data Index: 538594 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1454416 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6987. Min Act: -0.0000

Data Index: 797200 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1452342 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1487560 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7051. Min Act: -0.0000

Data Index: 234306 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6839. Min Act: -0.0000

Data Index: 583190 (The Pile)

Max Activating Token Index: 242

Text #15

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1485456 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1701952 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1453992 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1797796 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6349. Min Act: -0.0000

Data Index: 129712 (The Pile)

Max Activating Token Index: 931