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

Dataset: The Pile

Neuron 3305 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: 0.8372. Min Range: -0.8372

Max Act: 0.8343. Min Act: -0.0000

Data Index: 969875 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1549692 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1492527 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6982. Min Act: -0.0000

Data Index: 93818 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6775. Min Act: -0.0000

Data Index: 3819 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1414537 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1199035 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6955. Min Act: -0.0000

Data Index: 288891 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6766. Min Act: -0.0000

Data Index: 19779 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1877433 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6639. Min Act: -0.0000

Data Index: 650841 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1307546 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1122632 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6108. Min Act: -0.0000

Data Index: 772666 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1729969 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6192. Min Act: -0.0000

Data Index: 218762 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6154. Min Act: -0.0000

Data Index: 304476 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1609678 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6176. Min Act: -0.0000

Data Index: 812722 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6078. Min Act: -0.0000

Data Index: 760950 (The Pile)

Max Activating Token Index: 773