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

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

Neuron 5795 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: 0.1447. Min Range: -0.1447

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1279034 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1303486 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1320. Min Act: -0.0001

Data Index: 142618 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1300. Min Act: -0.0001

Data Index: 660157 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1324. Min Act: -0.0001

Data Index: 629453 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1307. Min Act: -0.0001

Data Index: 781059 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1232. Min Act: -0.0001

Data Index: 540940 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1225. Min Act: -0.0001

Data Index: 604740 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1211. Min Act: -0.0001

Data Index: 98175 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1191. Min Act: -0.0001

Data Index: 58940 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1250033 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1105. Min Act: -0.0001

Data Index: 456686 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1096. Min Act: -0.0001

Data Index: 788568 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1221. Min Act: -0.0002

Data Index: 463756 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1308518 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1034. Min Act: -0.0001

Data Index: 436904 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1102. Min Act: -0.0001

Data Index: 945117 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1009744 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1053. Min Act: -0.0001

Data Index: 430241 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.1447. Min Range: -0.1447

Max Act: 0.1049. Min Act: -0.0001

Data Index: 348758 (C4 (Web Text))

Max Activating Token Index: 593