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

Dataset: The Pile

Neuron 544 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1222580 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1194643 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1102714 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1647556 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3865. Min Act: -0.0000

Data Index: 642387 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1758683 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1763725 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3766. Min Act: -0.0000

Data Index: 108999 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3197. Min Act: -0.0000

Data Index: 797902 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3314. Min Act: -0.0000

Data Index: 802619 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3231. Min Act: -0.0000

Data Index: 451833 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1049592 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.2901. Min Act: -0.0000

Data Index: 425210 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3094. Min Act: -0.0000

Data Index: 16680 (The Pile)

Max Activating Token Index: 667

Text #14

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3376. Min Act: -0.0000

Data Index: 798470 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1544642 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.2972. Min Act: -0.0000

Data Index: 773803 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3339. Min Act: -0.0000

Data Index: 888663 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1403766 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1987463 (The Pile)

Max Activating Token Index: 652