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

Dataset: The Pile

Neuron 1811 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: 1.6133. Min Range: -1.6133

Max Act: 1.6133. Min Act: -0.0000

Data Index: 1389702 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2804. Min Act: -0.0000

Data Index: 444533 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2376. Min Act: -0.0000

Data Index: 786592 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1765736 (The Pile)

Max Activating Token Index: 423

Text #4

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2348. Min Act: -0.0000

Data Index: 700124 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.2166. Min Act: -0.0000

Data Index: 1577455 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.1104. Min Act: -0.0000

Data Index: 275450 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0675. Min Act: -0.0000

Data Index: 636513 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1328608 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0642. Min Act: -0.0000

Data Index: 649051 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0297. Min Act: -0.0000

Data Index: 253568 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1490886 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0007. Min Act: -0.0000

Data Index: 839704 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1098824 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1034997 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 1.6133. Min Range: -1.6133

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1747045 (The Pile)

Max Activating Token Index: 963

Text #16

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.9758. Min Act: -0.0000

Data Index: 809845 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.9913. Min Act: -0.0000

Data Index: 196346 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1826017 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 1.6133. Min Range: -1.6133

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1305496 (The Pile)

Max Activating Token Index: 998