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

Dataset: The Pile

Neuron 2558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1408826 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7452. Min Act: -0.0000

Data Index: 409346 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7179. Min Act: -0.0000

Data Index: 3593 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1915695 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7349. Min Act: -0.0000

Data Index: 419944 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6954. Min Act: -0.0000

Data Index: 182696 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7269. Min Act: -0.0000

Data Index: 465787 (The Pile)

Max Activating Token Index: 689

Text #7

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1031078 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6738. Min Act: -0.0000

Data Index: 819944 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6509. Min Act: -0.0000

Data Index: 217503 (The Pile)

Max Activating Token Index: 926

Text #10

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6868. Min Act: -0.0000

Data Index: 689024 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1014864 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1649171 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1730030 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1026188 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1190620 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1103250 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6232. Min Act: -0.0000

Data Index: 365687 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6622. Min Act: -0.0000

Data Index: 630149 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6341. Min Act: -0.0000

Data Index: 275278 (The Pile)

Max Activating Token Index: 560