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

Dataset: The Pile

Neuron 3390 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.8219. Min Act: -0.0000

Data Index: 1416578 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.9005. Min Act: -0.0000

Data Index: 48876 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.8670. Min Act: -0.0000

Data Index: 401572 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.8421. Min Act: -0.0000

Data Index: 429911 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.7193. Min Act: -0.0000

Data Index: 1190855 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.7095. Min Act: -0.0000

Data Index: 1458171 (The Pile)

Max Activating Token Index: 38

Text #6

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.6502. Min Act: -0.0000

Data Index: 1935114 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.6184. Min Act: -0.0000

Data Index: 594413 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.5213. Min Act: -0.0000

Data Index: 393317 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1204704 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.4373. Min Act: -0.0000

Data Index: 937312 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1612891 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.4788. Min Act: -0.0000

Data Index: 861552 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.4845. Min Act: -0.0000

Data Index: 390547 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.5074. Min Act: -0.0000

Data Index: 1785128 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.5012. Min Act: -0.0000

Data Index: 34260 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1048070 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1934400 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.4001. Min Act: -0.0000

Data Index: 1409362 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 1.9005. Min Range: -1.9005

Max Act: 1.4849. Min Act: -0.0000

Data Index: 1707291 (The Pile)

Max Activating Token Index: 264