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

Dataset: The Pile

Neuron 3771 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: 1.6119. Min Range: -1.6119

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1275808 (The Pile)

Max Activating Token Index: 260

Text #1

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2368. Min Act: -0.0000

Data Index: 253871 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1517588 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2620. Min Act: -0.0000

Data Index: 255906 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1905. Min Act: -0.0000

Data Index: 1163537 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1232468 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.0234. Min Act: 0.0000

Data Index: 607891 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.0225. Min Act: -0.0000

Data Index: 568208 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1331146 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.9348. Min Act: -0.0000

Data Index: 911123 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.7806. Min Act: -0.0000

Data Index: 270399 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.7928. Min Act: -0.0000

Data Index: 705417 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.8130. Min Act: -0.0000

Data Index: 476443 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1477521 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.7114. Min Act: -0.0000

Data Index: 481142 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.7317. Min Act: -0.0000

Data Index: 969352 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.7650. Min Act: -0.0000

Data Index: 844445 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1431143 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.6854. Min Act: -0.0000

Data Index: 803531 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 1.6119. Min Range: -1.6119

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1397918 (The Pile)

Max Activating Token Index: 67