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

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

Neuron 4649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0710. Min Act: -0.0000

Data Index: 504082 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1066658 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8375. Min Act: -0.0000

Data Index: 34186 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8119. Min Act: -0.0000

Data Index: 123855 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7813. Min Act: -0.0000

Data Index: 366388 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7500. Min Act: -0.0000

Data Index: 397827 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1258879 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7912. Min Act: -0.0000

Data Index: 31952 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1188828 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7549. Min Act: -0.0000

Data Index: 633510 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1225673 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7067. Min Act: -0.0000

Data Index: 113108 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7051. Min Act: -0.0000

Data Index: 617331 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1033073 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7210. Min Act: -0.0000

Data Index: 370323 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.6474. Min Act: -0.0000

Data Index: 770314 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7118. Min Act: -0.0000

Data Index: 54487 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.6295. Min Act: -0.0000

Data Index: 433269 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7109. Min Act: -0.0000

Data Index: 663940 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7000. Min Act: -0.0000

Data Index: 460078 (C4 (Web Text))

Max Activating Token Index: 349