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

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

Neuron 1472 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: 0.1173. Min Range: -0.1173

Max Act: 0.1173. Min Act: -0.0002

Data Index: 484971 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1169. Min Act: -0.0002

Data Index: 991236 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1135. Min Act: -0.0002

Data Index: 295717 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1471725 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1148. Min Act: -0.0002

Data Index: 66249 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1102. Min Act: -0.0002

Data Index: 863363 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1084. Min Act: -0.0002

Data Index: 807937 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1084. Min Act: -0.0002

Data Index: 923023 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1158696 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1350453 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1070. Min Act: -0.0002

Data Index: 311179 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1068. Min Act: -0.0002

Data Index: 513246 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1066. Min Act: -0.0002

Data Index: 464032 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1067. Min Act: -0.0002

Data Index: 587163 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1066. Min Act: -0.0002

Data Index: 454265 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1064. Min Act: -0.0002

Data Index: 247312 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1156668 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1058. Min Act: -0.0002

Data Index: 773682 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1059. Min Act: -0.0002

Data Index: 585619 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1051. Min Act: -0.0002

Data Index: 626729 (C4 (Web Text))

Max Activating Token Index: 138