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

Dataset: The Pile

Neuron 2910 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: 1.5100. Min Range: -1.5100

Max Act: 1.5100. Min Act: -0.0000

Data Index: 12487 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.5010. Min Act: -0.0000

Data Index: 609091 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3524. Min Act: -0.0000

Data Index: 392021 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.4455. Min Act: -0.0000

Data Index: 613837 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2254. Min Act: -0.0000

Data Index: 1461026 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3638. Min Act: -0.0000

Data Index: 380934 (The Pile)

Max Activating Token Index: 225

Text #6

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1132237 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1792568 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3053. Min Act: -0.0000

Data Index: 1042663 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3290. Min Act: -0.0000

Data Index: 690259 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1380411 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1915516 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1385369 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1926159 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1870866 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0256. Min Act: -0.0000

Data Index: 391473 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1964652 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1654805 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0210. Min Act: -0.0000

Data Index: 1006837 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.0347. Min Act: -0.0000

Data Index: 1832171 (The Pile)

Max Activating Token Index: 428