Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 721 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0005

Data Index: 177493 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0144. Min Act: -0.0005

Data Index: 193908 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0142. Min Act: -0.0006

Data Index: 798938 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1265245 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0133. Min Act: -0.0006

Data Index: 338929 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1027585 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0131. Min Act: -0.0006

Data Index: 510093 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0132. Min Act: -0.0006

Data Index: 309660 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0130. Min Act: -0.0006

Data Index: 738048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0130. Min Act: -0.0006

Data Index: 247256 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0131. Min Act: -0.0006

Data Index: 863697 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0129. Min Act: -0.0006

Data Index: 339173 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1571327 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0127. Min Act: -0.0006

Data Index: 875065 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0130. Min Act: -0.0005

Data Index: 370830 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1046491 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0129. Min Act: -0.0006

Data Index: 302952 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0129. Min Act: -0.0006

Data Index: 699763 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0127. Min Act: -0.0005

Data Index: 727001 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0127. Min Act: -0.0006

Data Index: 573711 (C4 (Web Text))

Max Activating Token Index: 541