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

Dataset: The Pile

Neuron 2669 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4340. Min Act: -0.0000

Data Index: 669599 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1642895 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3787. Min Act: -0.0000

Data Index: 706162 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3555. Min Act: -0.0000

Data Index: 398588 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3602. Min Act: -0.0000

Data Index: 501352 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1707754 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3074. Min Act: -0.0000

Data Index: 36265 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1651261 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2997. Min Act: -0.0000

Data Index: 582295 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3088. Min Act: -0.0000

Data Index: 375802 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1134695 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2877. Min Act: -0.0000

Data Index: 723490 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2960. Min Act: -0.0000

Data Index: 439564 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1533515 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2907. Min Act: -0.0000

Data Index: 912657 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2716. Min Act: -0.0000

Data Index: 640928 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2608. Min Act: -0.0000

Data Index: 238642 (The Pile)

Max Activating Token Index: 26

Text #17

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1293858 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2774. Min Act: -0.0000

Data Index: 607421 (The Pile)

Max Activating Token Index: 708

Text #19

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2794. Min Act: -0.0000

Data Index: 64187 (The Pile)

Max Activating Token Index: 435