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

Dataset: The Pile

Neuron 2743 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: 0.3451. Min Range: -0.3451

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1544182 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1266278 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1360471 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1585302 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1150996 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2347. Min Act: -0.0000

Data Index: 47831 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1276355 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2393. Min Act: -0.0000

Data Index: 972084 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2246. Min Act: -0.0000

Data Index: 407747 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2237. Min Act: -0.0000

Data Index: 917699 (The Pile)

Max Activating Token Index: 69

Text #10

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1877502 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2185. Min Act: -0.0000

Data Index: 3982 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1802481 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1985. Min Act: -0.0000

Data Index: 575401 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2023. Min Act: -0.0000

Data Index: 466240 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1129405 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2003. Min Act: -0.0000

Data Index: 575472 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1331609 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.1692. Min Act: -0.0000

Data Index: 529040 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1058470 (The Pile)

Max Activating Token Index: 329