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

Dataset: The Pile

Neuron 3470 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: 0.9145. Min Range: -0.9145

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1678838 (The Pile)

Max Activating Token Index: 841

Text #1

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1859766 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8661. Min Act: -0.0000

Data Index: 476973 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7047. Min Act: -0.0000

Data Index: 26115 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7253. Min Act: -0.0000

Data Index: 101937 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6998. Min Act: -0.0000

Data Index: 357567 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8000. Min Act: -0.0000

Data Index: 999966 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8068. Min Act: -0.0000

Data Index: 949567 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1472925 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7704. Min Act: -0.0000

Data Index: 204318 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8359. Min Act: -0.0000

Data Index: 959000 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1045767 (The Pile)

Max Activating Token Index: 665

Text #12

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7178. Min Act: -0.0000

Data Index: 390460 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6947. Min Act: -0.0000

Data Index: 956475 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7403. Min Act: -0.0000

Data Index: 982601 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1256510 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1331784 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7545. Min Act: -0.0000

Data Index: 495264 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1636894 (The Pile)

Max Activating Token Index: 919

Text #19

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6466. Min Act: -0.0000

Data Index: 748067 (The Pile)

Max Activating Token Index: 491