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

Dataset: The Pile

Neuron 2750 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.3963. Min Act: -0.0000

Data Index: 949252 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.3194. Min Act: -0.0000

Data Index: 1017414 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1687280 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.2597. Min Act: -0.0000

Data Index: 1072110 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1710119 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1797. Min Act: -0.0000

Data Index: 164484 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1060212 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.2059. Min Act: -0.0000

Data Index: 209046 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1148996 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1384717 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1329811 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1285838 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0871. Min Act: -0.0000

Data Index: 630660 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1131. Min Act: -0.0000

Data Index: 16876 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0781. Min Act: -0.0000

Data Index: 719377 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1029. Min Act: -0.0000

Data Index: 139992 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1758686 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0362. Min Act: -0.0000

Data Index: 941635 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1633247 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 1.3963. Min Range: -1.3963

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1971567 (The Pile)

Max Activating Token Index: 458