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

Dataset: The Pile

Neuron 495 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: 1.7793. Min Range: -1.7793

Max Act: 1.7793. Min Act: -0.0000

Data Index: 1435165 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.2676. Min Act: -0.0000

Data Index: 730183 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.2816. Min Act: -0.0000

Data Index: 667796 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1456330 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.1383. Min Act: -0.0000

Data Index: 209036 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1531680 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.0623. Min Act: -0.0000

Data Index: 448562 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.0525. Min Act: -0.0000

Data Index: 701621 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.8958. Min Act: -0.0000

Data Index: 127615 (The Pile)

Max Activating Token Index: 607

Text #9

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1332595 (The Pile)

Max Activating Token Index: 49

Text #10

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.9256. Min Act: -0.0000

Data Index: 287128 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.9840. Min Act: -0.0000

Data Index: 983145 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 1.7793. Min Range: -1.7793

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1263716 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.9211. Min Act: -0.0000

Data Index: 907562 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.9121. Min Act: 0.0000

Data Index: 1602653 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1888881 (The Pile)

Max Activating Token Index: 912

Text #16

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1761075 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.8919. Min Act: -0.0000

Data Index: 925610 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.9311. Min Act: -0.0000

Data Index: 367264 (The Pile)

Max Activating Token Index: 972

Text #19

Max Range: 1.7793. Min Range: -1.7793

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1329691 (The Pile)

Max Activating Token Index: 494