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

Dataset: The Pile

Neuron 3083 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: 7.0620. Min Range: -7.0620

Max Act: 7.0620. Min Act: -0.0000

Data Index: 1376581 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 7.0620. Min Range: -7.0620

Max Act: 6.3698. Min Act: -0.0000

Data Index: 529936 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 7.0620. Min Range: -7.0620

Max Act: 6.5666. Min Act: -0.0000

Data Index: 61989 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 7.0620. Min Range: -7.0620

Max Act: 6.3112. Min Act: -0.0000

Data Index: 1816402 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 7.0620. Min Range: -7.0620

Max Act: 6.5144. Min Act: -0.0000

Data Index: 1014129 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 7.0620. Min Range: -7.0620

Max Act: 6.4618. Min Act: -0.0000

Data Index: 1952792 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.1670. Min Act: -0.0000

Data Index: 1704668 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 7.0620. Min Range: -7.0620

Max Act: 6.0573. Min Act: -0.0000

Data Index: 1839319 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.7928. Min Act: -0.0000

Data Index: 191017 (The Pile)

Max Activating Token Index: 988

Text #9

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.9867. Min Act: -0.0000

Data Index: 490967 (The Pile)

Max Activating Token Index: 534

Text #10

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.9858. Min Act: -0.0000

Data Index: 624224 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.6600. Min Act: -0.0000

Data Index: 124525 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.5969. Min Act: -0.0000

Data Index: 1243108 (The Pile)

Max Activating Token Index: 840

Text #13

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.6796. Min Act: -0.0000

Data Index: 1375345 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.8911. Min Act: -0.0000

Data Index: 219958 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.6964. Min Act: -0.0000

Data Index: 681123 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 7.0620. Min Range: -7.0620

Max Act: 6.0434. Min Act: -0.0000

Data Index: 1773672 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.7963. Min Act: -0.0000

Data Index: 692365 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.9179. Min Act: -0.0000

Data Index: 1254953 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 7.0620. Min Range: -7.0620

Max Act: 5.9137. Min Act: -0.0000

Data Index: 1919365 (The Pile)

Max Activating Token Index: 975