Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1099 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.7450. Min Act: -0.0000

Data Index: 461902 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.5132. Min Act: -0.0000

Data Index: 698461 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.5215. Min Act: -0.0000

Data Index: 253560 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4050. Min Act: -0.0000

Data Index: 69411 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.2755. Min Act: -0.0000

Data Index: 662411 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4205. Min Act: -0.0000

Data Index: 733472 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1868. Min Act: 0.0000

Data Index: 778202 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1075660 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1521176 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1281938 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0296. Min Act: -0.0000

Data Index: 1951388 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1016. Min Act: -0.0000

Data Index: 236088 (The Pile)

Max Activating Token Index: 932

Text #12

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.2115. Min Act: -0.0000

Data Index: 1374972 (The Pile)

Max Activating Token Index: 495

Text #13

Max Range: 1.7450. Min Range: -1.7450

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1589793 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1484037 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1355248 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1600096 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1303887 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0191. Min Act: -0.0000

Data Index: 568167 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 1.7450. Min Range: -1.7450

Max Act: 0.9909. Min Act: 0.0000

Data Index: 845795 (The Pile)

Max Activating Token Index: 661