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

Dataset: The Pile

Neuron 1350 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: 1.2949. Min Range: -1.2949

Max Act: 1.2949. Min Act: -0.0000

Data Index: 1932442 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 1.2949. Min Range: -1.2949

Max Act: 1.1556. Min Act: -0.0000

Data Index: 697377 (The Pile)

Max Activating Token Index: 991

Text #2

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1017105 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.8996. Min Act: -0.0000

Data Index: 395014 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1241653 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.6981. Min Act: -0.0000

Data Index: 713927 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1365533 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.8045. Min Act: -0.0000

Data Index: 287975 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.6938. Min Act: -0.0001

Data Index: 780563 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.8082. Min Act: -0.0000

Data Index: 615971 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.6805. Min Act: -0.0000

Data Index: 649645 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1095343 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1863532 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1530002 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.7428. Min Act: -0.0000

Data Index: 569851 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1583694 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.6682. Min Act: -0.0000

Data Index: 414379 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.7656. Min Act: -0.0001

Data Index: 1865098 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.6490. Min Act: -0.0000

Data Index: 518907 (The Pile)

Max Activating Token Index: 47

Text #19

Max Range: 1.2949. Min Range: -1.2949

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1301486 (The Pile)

Max Activating Token Index: 384