Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1470 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1309600 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1212. Min Act: -0.0002

Data Index: 984006 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1160. Min Act: -0.0002

Data Index: 261121 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1282925 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1166. Min Act: -0.0000

Data Index: 497643 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1337688 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1119092 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1126128 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1128849 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1082. Min Act: -0.0002

Data Index: 824086 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1040511 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1122039 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1224984 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1094. Min Act: -0.0002

Data Index: 714794 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1036791 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1086. Min Act: -0.0002

Data Index: 721296 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1098794 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1070. Min Act: -0.0001

Data Index: 806290 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1268525 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1070. Min Act: -0.0002

Data Index: 23922 (C4 (Web Text))

Max Activating Token Index: 447