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

Dataset: The Pile

Neuron 1020 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.1043. Min Act: -0.0000

Data Index: 974953 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0835. Min Act: -0.0000

Data Index: 887023 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0971. Min Act: -0.0000

Data Index: 819598 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1277282 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1796585 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1291971 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9550. Min Act: -0.0000

Data Index: 159682 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9512. Min Act: -0.0000

Data Index: 980117 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9971. Min Act: -0.0000

Data Index: 193315 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9883. Min Act: -0.0000

Data Index: 664825 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1084843 (The Pile)

Max Activating Token Index: 61

Text #11

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9205. Min Act: -0.0000

Data Index: 474861 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1310384 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1526014 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9279. Min Act: -0.0000

Data Index: 432539 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8828. Min Act: -0.0000

Data Index: 436693 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1313838 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1968237 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.9473. Min Act: -0.0000

Data Index: 282948 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 1.1043. Min Range: -1.1043

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1318752 (The Pile)

Max Activating Token Index: 993