Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3579 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1077741 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1202. Min Act: -0.0000

Data Index: 713569 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1167224 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1074455 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1113. Min Act: -0.0000

Data Index: 7098 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1065707 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1080. Min Act: -0.0000

Data Index: 711794 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1114. Min Act: -0.0000

Data Index: 341676 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1032. Min Act: -0.0000

Data Index: 363758 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1106. Min Act: -0.0000

Data Index: 83584 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1087. Min Act: -0.0000

Data Index: 956444 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1079. Min Act: -0.0000

Data Index: 206997 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1074. Min Act: -0.0000

Data Index: 121109 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1184591 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1309725 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1036308 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1016. Min Act: -0.0000

Data Index: 438593 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1272372 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0983. Min Act: -0.0000

Data Index: 40962 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0976. Min Act: -0.0000

Data Index: 933550 (C4 (Web Text))

Max Activating Token Index: 774