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

Dataset: The Pile

Neuron 4549 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: 0.9166. Min Range: -0.9166

Max Act: 0.9166. Min Act: -0.0000

Data Index: 524445 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1479084 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7379. Min Act: -0.0000

Data Index: 132715 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7368. Min Act: -0.0000

Data Index: 17492 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7263. Min Act: -0.0000

Data Index: 213865 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6974. Min Act: -0.0000

Data Index: 864784 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1167582 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6835. Min Act: -0.0000

Data Index: 373737 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1937498 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7072. Min Act: -0.0000

Data Index: 23810 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6372. Min Act: -0.0000

Data Index: 390174 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6875. Min Act: -0.0000

Data Index: 736063 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6724. Min Act: -0.0000

Data Index: 504053 (The Pile)

Max Activating Token Index: 257

Text #13

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6738. Min Act: -0.0000

Data Index: 370434 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6249. Min Act: -0.0000

Data Index: 419366 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1170562 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1094035 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1990647 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1959405 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6532. Min Act: -0.0000

Data Index: 928896 (The Pile)

Max Activating Token Index: 199