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

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

Neuron 3033 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1163. Min Act: -0.0001

Data Index: 482034 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1062. Min Act: -0.0001

Data Index: 38237 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1034995 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1141092 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1057. Min Act: -0.0001

Data Index: 668094 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1056. Min Act: -0.0001

Data Index: 252849 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1076. Min Act: -0.0001

Data Index: 946047 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1029. Min Act: -0.0001

Data Index: 592298 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1032. Min Act: -0.0001

Data Index: 521497 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0976. Min Act: -0.0001

Data Index: 700537 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1101220 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1002. Min Act: -0.0001

Data Index: 842428 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1190673 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1001. Min Act: -0.0001

Data Index: 926977 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0949. Min Act: -0.0001

Data Index: 608224 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0978. Min Act: -0.0001

Data Index: 999082 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1333399 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1291217 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0877. Min Act: -0.0001

Data Index: 251593 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0924. Min Act: -0.0001

Data Index: 593605 (C4 (Web Text))

Max Activating Token Index: 44