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

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

Neuron 2008 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0076. Min Act: -0.0004

Data Index: 108765 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0080. Min Act: -0.0004

Data Index: 566401 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0081. Min Act: -0.0004

Data Index: 125474 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0076. Min Act: -0.0004

Data Index: 976549 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0071. Min Act: -0.0004

Data Index: 718689 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0071. Min Act: -0.0004

Data Index: 736978 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0072. Min Act: -0.0004

Data Index: 737981 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0070. Min Act: -0.0004

Data Index: 791162 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1501886 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1322245 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0061. Min Act: -0.0004

Data Index: 339165 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0053. Min Act: -0.0004

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1600270 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0066. Min Act: -0.0004

Data Index: 432973 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0066. Min Act: -0.0004

Data Index: 444472 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1358810 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0056. Min Act: -0.0004

Data Index: 8318 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0065. Min Act: -0.0004

Data Index: 819379 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0061. Min Act: -0.0004

Data Index: 787001 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0064. Min Act: -0.0004

Data Index: 840919 (C4 (Web Text))

Max Activating Token Index: 959