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

Dataset: The Pile

Neuron 2313 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.9550. Min Act: -0.0000

Data Index: 334481 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 3.1009. Min Range: -3.1009

Max Act: 3.1009. Min Act: -0.0000

Data Index: 1269194 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.8840. Min Act: -0.0000

Data Index: 1523829 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 3.1009. Min Range: -3.1009

Max Act: 3.0002. Min Act: -0.0000

Data Index: 9796 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.9509. Min Act: -0.0000

Data Index: 195122 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.5781. Min Act: -0.0000

Data Index: 834642 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.6952. Min Act: -0.0000

Data Index: 1597076 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.8257. Min Act: -0.0000

Data Index: 200189 (The Pile)

Max Activating Token Index: 127

Text #8

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.8302. Min Act: -0.0000

Data Index: 40600 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.6467. Min Act: -0.0000

Data Index: 1832699 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.7803. Min Act: -0.0000

Data Index: 1029922 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.6140. Min Act: -0.0000

Data Index: 464431 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.7278. Min Act: -0.0000

Data Index: 1120120 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.5918. Min Act: -0.0000

Data Index: 1977279 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.6976. Min Act: -0.0000

Data Index: 1103700 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.6980. Min Act: -0.0000

Data Index: 933051 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.5544. Min Act: -0.0000

Data Index: 1447807 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.4126. Min Act: -0.0000

Data Index: 1202012 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.9445. Min Act: -0.0000

Data Index: 966702 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 3.1009. Min Range: -3.1009

Max Act: 2.5369. Min Act: -0.0000

Data Index: 405904 (The Pile)

Max Activating Token Index: 471