Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2922 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.7006. Min Act: -0.0000

Data Index: 217989 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.5855. Min Act: -0.0000

Data Index: 327941 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1722348 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1934992 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1678415 (The Pile)

Max Activating Token Index: 767

Text #5

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1654086 (The Pile)

Max Activating Token Index: 212

Text #6

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.3067. Min Act: -0.0000

Data Index: 997911 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.2034. Min Act: -0.0000

Data Index: 508943 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.2206. Min Act: -0.0000

Data Index: 661311 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1825927 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.1719. Min Act: -0.0000

Data Index: 140246 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.1972. Min Act: -0.0000

Data Index: 1281754 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1018946 (The Pile)

Max Activating Token Index: 128

Text #13

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0863. Min Act: -0.0000

Data Index: 270424 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 1.7006. Min Range: -1.7006

Max Act: 0.9848. Min Act: -0.0000

Data Index: 111579 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.1193. Min Act: -0.0000

Data Index: 712075 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0959. Min Act: -0.0000

Data Index: 1241941 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 1.7006. Min Range: -1.7006

Max Act: 0.9929. Min Act: -0.0000

Data Index: 446839 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0585. Min Act: 0.0000

Data Index: 711166 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0769. Min Act: -0.0000

Data Index: 103155 (The Pile)

Max Activating Token Index: 623