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

Dataset: The Pile

Neuron 25 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: 1.0681. Min Range: -1.0681

Max Act: 1.0681. Min Act: -0.0000

Data Index: 989848 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1801173 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7435. Min Act: -0.0000

Data Index: 110126 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7327. Min Act: -0.0000

Data Index: 815359 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1743105 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1173857 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6808. Min Act: -0.0000

Data Index: 416477 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1724039 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1240173 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6719. Min Act: -0.0000

Data Index: 966440 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6193. Min Act: -0.0000

Data Index: 129698 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1841589 (The Pile)

Max Activating Token Index: 7

Text #12

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6123. Min Act: -0.0000

Data Index: 316624 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1778774 (The Pile)

Max Activating Token Index: 92

Text #14

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.5877. Min Act: -0.0000

Data Index: 947423 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1531406 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1137744 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.5616. Min Act: -0.0000

Data Index: 918284 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.5604. Min Act: -0.0000

Data Index: 441143 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6122. Min Act: -0.0000

Data Index: 545210 (The Pile)

Max Activating Token Index: 659