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

Dataset: The Pile

Neuron 1099 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.7110. Min Act: -0.0000

Data Index: 752324 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1165125 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1675854 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1590802 (The Pile)

Max Activating Token Index: 25

Text #4

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1222200 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5789. Min Act: -0.0000

Data Index: 5034 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1691921 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5513. Min Act: -0.0000

Data Index: 238004 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1212022 (The Pile)

Max Activating Token Index: 452

Text #9

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1098303 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5849. Min Act: -0.0000

Data Index: 754392 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1302253 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5553. Min Act: -0.0000

Data Index: 258291 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5400. Min Act: -0.0000

Data Index: 11822 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1925187 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5654. Min Act: -0.0000

Data Index: 815517 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5328. Min Act: -0.0000

Data Index: 941673 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1835278 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5473. Min Act: -0.0000

Data Index: 965779 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1578553 (The Pile)

Max Activating Token Index: 347