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

Dataset: The Pile

Neuron 2163 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.7741. Min Act: -0.0000

Data Index: 747945 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.7424. Min Act: -0.0000

Data Index: 1267267 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.9167. Min Act: -0.0000

Data Index: 952077 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.7061. Min Act: -0.0000

Data Index: 1176478 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.9937. Min Act: -0.0000

Data Index: 861509 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.7565. Min Act: -0.0000

Data Index: 9810 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.3377. Min Act: -0.0000

Data Index: 1930097 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.9157. Min Act: -0.0000

Data Index: 1287986 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.2491. Min Act: -0.0000

Data Index: 1056207 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.4505. Min Act: -0.0000

Data Index: 1376352 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.6347. Min Act: -0.0000

Data Index: 702449 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.5779. Min Act: -0.0000

Data Index: 833458 (The Pile)

Max Activating Token Index: 9

Text #12

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.5160. Min Act: -0.0000

Data Index: 209480 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.1055. Min Act: -0.0000

Data Index: 1954442 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.4692. Min Act: -0.0000

Data Index: 1077558 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.4458. Min Act: -0.0000

Data Index: 339909 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.4133. Min Act: -0.0000

Data Index: 60979 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.2168. Min Act: -0.0000

Data Index: 873399 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.4096. Min Act: -0.0000

Data Index: 510946 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 5.9937. Min Range: -5.9937

Max Act: 5.4059. Min Act: -0.0000

Data Index: 686162 (The Pile)

Max Activating Token Index: 137