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

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

Neuron 2347 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: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0003

Data Index: 930836 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1466897 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0097. Min Act: -0.0003

Data Index: 671550 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0097. Min Act: -0.0003

Data Index: 938648 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0096. Min Act: -0.0003

Data Index: 107566 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0096. Min Act: -0.0003

Data Index: 298150 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0094. Min Act: -0.0003

Data Index: 372464 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0093. Min Act: -0.0004

Data Index: 1263152 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1256356 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0091. Min Act: -0.0004

Data Index: 410648 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0090. Min Act: -0.0003

Data Index: 955030 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0089. Min Act: -0.0003

Data Index: 1201052 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0089. Min Act: -0.0003

Data Index: 426658 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0003

Data Index: 695097 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1192721 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0083. Min Act: -0.0003

Data Index: 750331 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0081. Min Act: -0.0003

Data Index: 507501 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1394426 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1283089 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1107023 (C4 (Web Text))

Max Activating Token Index: 26