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

Dataset: The Pile

Neuron 2790 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0767. Min Range: -1.0767

Max Act: 1.0767. Min Act: -0.0000

Data Index: 988338 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 1.0767. Min Range: -1.0767

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1865183 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 1.0767. Min Range: -1.0767

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1474972 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1291401 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9929. Min Act: -0.0000

Data Index: 944625 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1924350 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9153. Min Act: -0.0000

Data Index: 783142 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9008. Min Act: -0.0000

Data Index: 734163 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9431. Min Act: -0.0000

Data Index: 217320 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1739532 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1736477 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1974649 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9224. Min Act: -0.0000

Data Index: 322110 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8721. Min Act: -0.0000

Data Index: 485476 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9048. Min Act: -0.0000

Data Index: 769458 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8229. Min Act: -0.0000

Data Index: 898546 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9146. Min Act: -0.0000

Data Index: 887937 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8124. Min Act: -0.0000

Data Index: 993211 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1514299 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1424057 (The Pile)

Max Activating Token Index: 925