Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2845 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0004

Data Index: 66050 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0087. Min Act: -0.0004

Data Index: 146754 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0087. Min Act: -0.0004

Data Index: 500760 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0087. Min Act: -0.0004

Data Index: 675028 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1243265 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0085. Min Act: -0.0004

Data Index: 559826 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0004

Data Index: 1213301 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1329694 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0004

Data Index: 973207 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0004

Data Index: 1149349 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0004

Data Index: 1151673 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0004

Data Index: 1161626 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0004

Data Index: 1098086 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0004

Data Index: 1164957 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0004

Data Index: 149452 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0004

Data Index: 36262 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0004

Data Index: 923429 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 859226 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 790349 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0004

Data Index: 1092996 (C4 (Web Text))

Max Activating Token Index: 830