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

Dataset: The Pile

Neuron 1456 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1051275 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.4966. Min Act: -0.0000

Data Index: 1336968 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.4048. Min Act: -0.0000

Data Index: 397219 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3908. Min Act: -0.0000

Data Index: 99844 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1747064 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3794. Min Act: -0.0000

Data Index: 50481 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.2819. Min Act: -0.0000

Data Index: 1659032 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3556. Min Act: -0.0000

Data Index: 814872 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3355. Min Act: -0.0000

Data Index: 599337 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3128. Min Act: -0.0000

Data Index: 647989 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3982. Min Act: -0.0000

Data Index: 1233875 (The Pile)

Max Activating Token Index: 313

Text #11

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3230. Min Act: -0.0000

Data Index: 24306 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1470909 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1270945 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.2561. Min Act: -0.0000

Data Index: 1053704 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.1763. Min Act: -0.0000

Data Index: 413787 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1794973 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.2310. Min Act: -0.0000

Data Index: 283396 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.2151. Min Act: 0.0000

Data Index: 1983171 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 1.4966. Min Range: -1.4966

Max Act: 1.1403. Min Act: -0.0000

Data Index: 21960 (The Pile)

Max Activating Token Index: 146