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

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

Neuron 1245 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1403. Min Act: -0.0000

Data Index: 196904 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1220. Min Act: -0.0000

Data Index: 376940 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1235. Min Act: -0.0000

Data Index: 516026 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1141. Min Act: 0.0000

Data Index: 805324 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1219. Min Act: -0.0000

Data Index: 793230 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1341054 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1097. Min Act: -0.0000

Data Index: 531445 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1075. Min Act: -0.0000

Data Index: 837901 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1108. Min Act: -0.0000

Data Index: 121184 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1028. Min Act: -0.0000

Data Index: 306189 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1357171 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1006. Min Act: -0.0000

Data Index: 208373 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1040. Min Act: -0.0000

Data Index: 404981 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1035. Min Act: -0.0000

Data Index: 760386 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1073. Min Act: -0.0000

Data Index: 104163 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1226297 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0923. Min Act: -0.0000

Data Index: 987467 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0992. Min Act: -0.0000

Data Index: 309984 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1057557 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1010. Min Act: -0.0000

Data Index: 795578 (C4 (Web Text))

Max Activating Token Index: 564