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

Dataset: The Pile

Neuron 3916 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: 0.4545. Min Range: -0.4545

Max Act: 0.4545. Min Act: -0.0000

Data Index: 803956 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4188. Min Act: -0.0000

Data Index: 626425 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4056. Min Act: -0.0000

Data Index: 834038 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1025450 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3970. Min Act: -0.0000

Data Index: 418921 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3810. Min Act: -0.0000

Data Index: 548153 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1053785 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3637. Min Act: -0.0000

Data Index: 908144 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3601. Min Act: -0.0000

Data Index: 138741 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1614077 (The Pile)

Max Activating Token Index: 755

Text #10

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3555. Min Act: -0.0000

Data Index: 645635 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1093333 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1637358 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3591. Min Act: -0.0000

Data Index: 180244 (The Pile)

Max Activating Token Index: 53

Text #14

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1693013 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3443. Min Act: -0.0000

Data Index: 327998 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1058468 (The Pile)

Max Activating Token Index: 822

Text #17

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3433. Min Act: -0.0000

Data Index: 177612 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3267. Min Act: -0.0000

Data Index: 160092 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 0.4545. Min Range: -0.4545

Max Act: 0.3587. Min Act: -0.0000

Data Index: 591911 (The Pile)

Max Activating Token Index: 757