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

Dataset: The Pile

Neuron 2069 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.1969. Min Act: -0.0000

Data Index: 480002 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1131911 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.2554. Min Act: -0.0000

Data Index: 911402 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1226605 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1715637 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1993780 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.1173. Min Act: -0.0000

Data Index: 675756 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1192502 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1774171 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.1012. Min Act: -0.0000

Data Index: 1779841 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0336. Min Act: -0.0000

Data Index: 507407 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0548. Min Act: -0.0000

Data Index: 251078 (The Pile)

Max Activating Token Index: 7

Text #12

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1333302 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1664639 (The Pile)

Max Activating Token Index: 10

Text #14

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.1051. Min Act: -0.0000

Data Index: 808522 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.1119. Min Act: -0.0000

Data Index: 1959239 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0639. Min Act: -0.0000

Data Index: 382511 (The Pile)

Max Activating Token Index: 980

Text #17

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1758064 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 1.2722. Min Range: -1.2722

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1559787 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 1.2722. Min Range: -1.2722

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1224382 (The Pile)

Max Activating Token Index: 920