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

Dataset: The Pile

Neuron 1304 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: 0.3356. Min Range: -0.3356

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1661748 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3077. Min Act: -0.0000

Data Index: 714039 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1924589 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1483043 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1377875 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3134. Min Act: -0.0000

Data Index: 749961 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3014. Min Act: -0.0000

Data Index: 542939 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1663678 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2847. Min Act: -0.0000

Data Index: 141451 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2805. Min Act: 0.0000

Data Index: 1625169 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2769. Min Act: -0.0000

Data Index: 354275 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2698. Min Act: -0.0000

Data Index: 467419 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2539. Min Act: -0.0000

Data Index: 511277 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1279833 (The Pile)

Max Activating Token Index: 771

Text #14

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1037287 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2702. Min Act: -0.0000

Data Index: 649771 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2589. Min Act: -0.0000

Data Index: 536835 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2685. Min Act: 0.0000

Data Index: 634557 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2583. Min Act: -0.0000

Data Index: 149100 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1922313 (The Pile)

Max Activating Token Index: 204