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

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

Neuron 4446 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0001

Data Index: 1135214 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0064. Min Act: -0.0001

Data Index: 832211 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0001

Data Index: 911888 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0062. Min Act: -0.0001

Data Index: 32342 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0062. Min Act: -0.0001

Data Index: 955373 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0058. Min Act: -0.0001

Data Index: 1466172 (Python Code)

Max Activating Token Index: 190

Text #6

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0058. Min Act: -0.0001

Data Index: 842577 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0058. Min Act: -0.0001

Data Index: 915734 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0057. Min Act: -0.0001

Data Index: 850736 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0057. Min Act: -0.0001

Data Index: 1169846 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0056. Min Act: -0.0001

Data Index: 965865 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0054. Min Act: -0.0001

Data Index: 719721 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0051. Min Act: -0.0001

Data Index: 422679 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0055. Min Act: -0.0001

Data Index: 764775 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0056. Min Act: -0.0001

Data Index: 486185 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0053. Min Act: -0.0001

Data Index: 1244837 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0053. Min Act: -0.0001

Data Index: 1089771 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1516949 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0055. Min Act: -0.0001

Data Index: 1055947 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0054. Min Act: -0.0001

Data Index: 164252 (C4 (Web Text))

Max Activating Token Index: 410