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

Dataset: The Pile

Neuron 2251 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: 1.7844. Min Range: -1.7844

Max Act: 1.7844. Min Act: -0.0000

Data Index: 341368 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6047. Min Act: -0.0000

Data Index: 1222342 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5982. Min Act: -0.0000

Data Index: 1171738 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6133. Min Act: -0.0000

Data Index: 1138062 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6074. Min Act: -0.0000

Data Index: 1978594 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5791. Min Act: -0.0000

Data Index: 534529 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5726. Min Act: -0.0000

Data Index: 1653292 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5734. Min Act: -0.0000

Data Index: 1252120 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5582. Min Act: -0.0000

Data Index: 812566 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6418. Min Act: -0.0000

Data Index: 1188292 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1179103 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5510. Min Act: -0.0000

Data Index: 157987 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5486. Min Act: 0.0000

Data Index: 883663 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5460. Min Act: -0.0000

Data Index: 510656 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6309. Min Act: 0.0000

Data Index: 1268468 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1226976 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1029732 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4088. Min Act: -0.0000

Data Index: 234494 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.3266. Min Act: -0.0000

Data Index: 146477 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 1.7844. Min Range: -1.7844

Max Act: 1.4992. Min Act: -0.0000

Data Index: 676560 (The Pile)

Max Activating Token Index: 984