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

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

Neuron 1164 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0003

Data Index: 434390 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0110. Min Act: -0.0003

Data Index: 271002 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0119. Min Act: -0.0003

Data Index: 166899 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0109. Min Act: -0.0003

Data Index: 520827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0003

Data Index: 676390 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0087. Min Act: -0.0003

Data Index: 152347 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0107. Min Act: -0.0003

Data Index: 55072 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1211370 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0096. Min Act: -0.0003

Data Index: 770888 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0101. Min Act: -0.0003

Data Index: 18618 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0104. Min Act: -0.0003

Data Index: 868732 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0094. Min Act: -0.0003

Data Index: 50817 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1147632 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0098. Min Act: -0.0003

Data Index: 277099 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0080. Min Act: -0.0003

Data Index: 588848 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0092. Min Act: -0.0003

Data Index: 455523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0099. Min Act: -0.0003

Data Index: 683517 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0098. Min Act: -0.0003

Data Index: 1192514 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0104. Min Act: -0.0003

Data Index: 820330 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0091. Min Act: -0.0003

Data Index: 573548 (C4 (Web Text))

Max Activating Token Index: 356