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

Dataset: The Pile

Neuron 2311 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.7660. Min Act: -0.0000

Data Index: 1981361 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 3.1059. Min Range: -3.1059

Max Act: 3.1059. Min Act: -0.0000

Data Index: 1484173 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.7976. Min Act: -0.0000

Data Index: 36867 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.4961. Min Act: -0.0000

Data Index: 657892 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.2868. Min Act: -0.0000

Data Index: 229369 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.2148. Min Act: -0.0000

Data Index: 1269994 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.0285. Min Act: -0.0000

Data Index: 1767950 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.1085. Min Act: -0.0000

Data Index: 1053845 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.2336. Min Act: -0.0000

Data Index: 1811762 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.9302. Min Act: -0.0000

Data Index: 1680714 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.6455. Min Act: -0.0000

Data Index: 1219102 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.7786. Min Act: -0.0000

Data Index: 571636 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.5622. Min Act: -0.0000

Data Index: 828933 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.7111. Min Act: -0.0000

Data Index: 1523103 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.5107. Min Act: -0.0000

Data Index: 965298 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.5216. Min Act: -0.0000

Data Index: 1572610 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.7589. Min Act: -0.0000

Data Index: 1879279 (The Pile)

Max Activating Token Index: 284

Text #17

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.5695. Min Act: -0.0000

Data Index: 805526 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.4094. Min Act: -0.0000

Data Index: 1865869 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 3.1059. Min Range: -3.1059

Max Act: 1.5454. Min Act: -0.0000

Data Index: 399000 (The Pile)

Max Activating Token Index: 363