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

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

Neuron 3951 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1238. Min Act: -0.0001

Data Index: 812142 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1574729 (Python Code)

Max Activating Token Index: 963

Text #2

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1163101 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1476640 (Python Code)

Max Activating Token Index: 870

Text #4

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1452212 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1590118 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1079. Min Act: -0.0001

Data Index: 6999 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1613677 (Python Code)

Max Activating Token Index: 841

Text #8

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1559910 (Python Code)

Max Activating Token Index: 369

Text #9

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1423895 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1496419 (Python Code)

Max Activating Token Index: 443

Text #11

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1552661 (Python Code)

Max Activating Token Index: 682

Text #12

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1520616 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1503770 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1543585 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1427853 (Python Code)

Max Activating Token Index: 494

Text #16

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1608258 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1446946 (Python Code)

Max Activating Token Index: 163

Text #18

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1619976 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0959. Min Act: -0.0001

Data Index: 767422 (C4 (Web Text))

Max Activating Token Index: 224