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

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

Neuron 2125 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: 0.1284. Min Range: -0.1284

Max Act: 0.1233. Min Act: -0.0001

Data Index: 843846 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1132484 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1024812 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1048. Min Act: -0.0001

Data Index: 280970 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1086987 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1231. Min Act: -0.0001

Data Index: 337636 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1034088 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1004. Min Act: -0.0001

Data Index: 460700 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1220863 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1071. Min Act: -0.0001

Data Index: 182040 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0845. Min Act: -0.0001

Data Index: 287749 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0994. Min Act: -0.0001

Data Index: 103559 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1027495 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0902. Min Act: -0.0001

Data Index: 498762 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1004. Min Act: -0.0001

Data Index: 280044 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1165151 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1114. Min Act: -0.0001

Data Index: 851091 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0905. Min Act: -0.0001

Data Index: 168123 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0956. Min Act: -0.0001

Data Index: 639383 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1153731 (C4 (Web Text))

Max Activating Token Index: 181