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

Dataset: The Pile

Neuron 780 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.7886. Min Act: -0.0000

Data Index: 778684 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1317289 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1888083 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.1848. Min Act: -0.0000

Data Index: 623162 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.1699. Min Act: -0.0000

Data Index: 829387 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0949. Min Act: -0.0000

Data Index: 367920 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1042240 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1173053 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1111619 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0278. Min Act: -0.0000

Data Index: 388348 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0939. Min Act: -0.0000

Data Index: 506007 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0278. Min Act: -0.0000

Data Index: 149746 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1034902 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1610925 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1392059 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0733. Min Act: -0.0000

Data Index: 444939 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0403. Min Act: -0.0000

Data Index: 1387512 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1902474 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0770. Min Act: -0.0000

Data Index: 546425 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 1.7886. Min Range: -1.7886

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1502520 (The Pile)

Max Activating Token Index: 776