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

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

Neuron 598 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2297. Min Act: -0.0002

Data Index: 772950 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2247. Min Act: -0.0002

Data Index: 530001 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2101. Min Act: -0.0002

Data Index: 228447 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2119. Min Act: -0.0002

Data Index: 91532 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2118. Min Act: -0.0002

Data Index: 152533 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2112. Min Act: -0.0002

Data Index: 1064892 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2106. Min Act: -0.0002

Data Index: 956333 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2106. Min Act: -0.0002

Data Index: 260212 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2100. Min Act: -0.0002

Data Index: 407219 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2094. Min Act: -0.0002

Data Index: 1023769 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2098. Min Act: -0.0002

Data Index: 600689 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2069. Min Act: -0.0002

Data Index: 1220778 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2142. Min Act: -0.0002

Data Index: 435806 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2064. Min Act: -0.0002

Data Index: 1200823 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2059. Min Act: -0.0002

Data Index: 354716 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2059. Min Act: -0.0002

Data Index: 1238605 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2054. Min Act: -0.0002

Data Index: 1139830 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2056. Min Act: -0.0002

Data Index: 1168774 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2057. Min Act: -0.0002

Data Index: 71345 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2053. Min Act: -0.0002

Data Index: 99565 (C4 (Web Text))

Max Activating Token Index: 13