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

Dataset: The Pile

Neuron 1607 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9970. Min Act: -0.0000

Data Index: 651696 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1649510 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9438. Min Act: -0.0000

Data Index: 647666 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8857. Min Act: -0.0000

Data Index: 183151 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1447302 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1396273 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9206. Min Act: -0.0000

Data Index: 680374 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9279. Min Act: -0.0000

Data Index: 580198 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1006530 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8908. Min Act: -0.0000

Data Index: 629739 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1169714 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1607067 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1733055 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8652. Min Act: -0.0001

Data Index: 1202590 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1166189 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1204437 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8349. Min Act: -0.0000

Data Index: 6245 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1292917 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1923528 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1491236 (The Pile)

Max Activating Token Index: 1004