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

Dataset: The Pile

Neuron 4160 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0397. Min Range: -1.0397

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1414514 (The Pile)

Max Activating Token Index: 249

Text #1

Max Range: 1.0397. Min Range: -1.0397

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1601577 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1420660 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.0397. Min Range: -1.0397

Max Act: 1.0026. Min Act: -0.0000

Data Index: 854927 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9709. Min Act: -0.0000

Data Index: 160692 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 1.0397. Min Range: -1.0397

Max Act: 1.0071. Min Act: -0.0000

Data Index: 901122 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1918092 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9305. Min Act: -0.0000

Data Index: 79466 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1324384 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1885690 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8176. Min Act: -0.0000

Data Index: 832962 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1147030 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8359. Min Act: -0.0000

Data Index: 253289 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.9934. Min Act: -0.0000

Data Index: 144762 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8336. Min Act: -0.0000

Data Index: 15992 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7864. Min Act: -0.0000

Data Index: 709661 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8055. Min Act: -0.0000

Data Index: 380569 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8482. Min Act: -0.0000

Data Index: 809842 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7824. Min Act: -0.0000

Data Index: 251984 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1753641 (The Pile)

Max Activating Token Index: 603