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

Dataset: The Pile

Neuron 3742 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: 0.5927. Min Range: -0.5927

Max Act: 0.5927. Min Act: -0.0000

Data Index: 889228 (The Pile)

Max Activating Token Index: 883

Text #1

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5527. Min Act: -0.0000

Data Index: 52227 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4771. Min Act: -0.0000

Data Index: 794289 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4492. Min Act: -0.0000

Data Index: 974152 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4394. Min Act: -0.0000

Data Index: 954789 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4474. Min Act: -0.0000

Data Index: 671994 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1417929 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1309278 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1037238 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1985294 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3996. Min Act: -0.0000

Data Index: 734712 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4053. Min Act: -0.0000

Data Index: 625062 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1003231 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3664. Min Act: -0.0000

Data Index: 86343 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1587549 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3347. Min Act: -0.0000

Data Index: 299483 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3223. Min Act: -0.0000

Data Index: 758957 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1961924 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3053. Min Act: -0.0000

Data Index: 344703 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.3037. Min Act: -0.0000

Data Index: 735556 (The Pile)

Max Activating Token Index: 791