Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1096 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1042. Min Act: -0.0001

Data Index: 667228 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1237. Min Act: -0.0001

Data Index: 311109 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1074. Min Act: -0.0001

Data Index: 708862 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1231217 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1079. Min Act: -0.0001

Data Index: 774805 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1026. Min Act: -0.0001

Data Index: 327840 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1050. Min Act: -0.0001

Data Index: 149199 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1045. Min Act: -0.0001

Data Index: 758440 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0969. Min Act: -0.0001

Data Index: 875457 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1042. Min Act: -0.0001

Data Index: 101405 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1061. Min Act: -0.0001

Data Index: 808264 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1012. Min Act: -0.0000

Data Index: 983721 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1267390 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1013. Min Act: -0.0001

Data Index: 479078 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1377206 (Python Code)

Max Activating Token Index: 167

Text #16

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1266869 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1299287 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1009958 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0984. Min Act: -0.0001

Data Index: 837433 (C4 (Web Text))

Max Activating Token Index: 282