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

Dataset: The Pile

Neuron 850 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: 0.7278. Min Range: -0.7278

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1038781 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1034429 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6682. Min Act: -0.0000

Data Index: 525777 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6666. Min Act: -0.0000

Data Index: 759360 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6431. Min Act: -0.0000

Data Index: 947778 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1585059 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6083. Min Act: -0.0000

Data Index: 88398 (The Pile)

Max Activating Token Index: 437

Text #7

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6055. Min Act: -0.0000

Data Index: 896552 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1863613 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5926. Min Act: -0.0000

Data Index: 102266 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1008121 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6014. Min Act: -0.0000

Data Index: 681632 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5826. Min Act: -0.0000

Data Index: 677053 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5742. Min Act: -0.0000

Data Index: 145220 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1115764 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1111795 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1405193 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6035. Min Act: -0.0000

Data Index: 719260 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5825. Min Act: -0.0000

Data Index: 976230 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1696802 (The Pile)

Max Activating Token Index: 840