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

Dataset: The Pile

Neuron 1933 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: 0.8885. Min Range: -0.8885

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1123985 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7328. Min Act: -0.0000

Data Index: 254484 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7181. Min Act: -0.0000

Data Index: 603663 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1765769 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1552287 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7207. Min Act: -0.0000

Data Index: 911653 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7301. Min Act: -0.0000

Data Index: 340412 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1205475 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6812. Min Act: -0.0000

Data Index: 247720 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6222. Min Act: -0.0000

Data Index: 467592 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1842445 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1245885 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1412767 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6526. Min Act: -0.0000

Data Index: 770867 (The Pile)

Max Activating Token Index: 92

Text #14

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6127. Min Act: -0.0000

Data Index: 167539 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6447. Min Act: -0.0000

Data Index: 628540 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6008. Min Act: -0.0000

Data Index: 357521 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6346. Min Act: -0.0000

Data Index: 608489 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1848107 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5817. Min Act: -0.0000

Data Index: 386 (The Pile)

Max Activating Token Index: 473