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

Dataset: The Pile

Neuron 1537 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0470. Min Range: -1.0470

Max Act: 1.0470. Min Act: -0.0000

Data Index: 413313 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.9050. Min Act: -0.0000

Data Index: 326425 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.8041. Min Act: -0.0000

Data Index: 223425 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1592800 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7396. Min Act: -0.0000

Data Index: 737097 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7844. Min Act: -0.0000

Data Index: 926658 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1310196 (The Pile)

Max Activating Token Index: 76

Text #7

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1212858 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1928105 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1670113 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.6268. Min Act: -0.0000

Data Index: 569590 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.6288. Min Act: -0.0000

Data Index: 852693 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.6645. Min Act: -0.0000

Data Index: 38941 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1861840 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.5655. Min Act: -0.0000

Data Index: 129900 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.5941. Min Act: -0.0000

Data Index: 951729 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.5583. Min Act: -0.0000

Data Index: 910274 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1032760 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1617244 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 1.0470. Min Range: -1.0470

Max Act: 0.5407. Min Act: -0.0000

Data Index: 929957 (The Pile)

Max Activating Token Index: 507