Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1974 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6086. Min Act: -0.0000

Data Index: 783445 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.8623. Min Act: -0.0000

Data Index: 1561186 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6404. Min Act: -0.0000

Data Index: 854433 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5266. Min Act: -0.0000

Data Index: 970528 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6498. Min Act: -0.0000

Data Index: 1985413 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4994. Min Act: -0.0000

Data Index: 1668461 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6236. Min Act: -0.0000

Data Index: 1021993 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4933. Min Act: -0.0000

Data Index: 416567 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1499406 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1995161 (The Pile)

Max Activating Token Index: 461

Text #10

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5658. Min Act: -0.0000

Data Index: 508286 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.3614. Min Act: -0.0000

Data Index: 507009 (The Pile)

Max Activating Token Index: 678

Text #12

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.3902. Min Act: -0.0000

Data Index: 946682 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4292. Min Act: -0.0000

Data Index: 1828043 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4195. Min Act: -0.0000

Data Index: 1494306 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1916162 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4279. Min Act: -0.0000

Data Index: 29838 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4217. Min Act: -0.0000

Data Index: 441916 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.3159. Min Act: -0.0000

Data Index: 146002 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1613992 (The Pile)

Max Activating Token Index: 966