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

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

Neuron 3566 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0001

Data Index: 410442 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1034583 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1027. Min Act: -0.0001

Data Index: 828471 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1051. Min Act: -0.0001

Data Index: 523125 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1083. Min Act: -0.0001

Data Index: 858450 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1251334 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1067. Min Act: -0.0001

Data Index: 982865 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1057. Min Act: -0.0001

Data Index: 968962 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1283019 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1014. Min Act: -0.0001

Data Index: 118287 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0905. Min Act: -0.0001

Data Index: 410381 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0996. Min Act: -0.0001

Data Index: 154615 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0922. Min Act: -0.0001

Data Index: 219311 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1121052 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0934. Min Act: -0.0001

Data Index: 70996 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0933. Min Act: -0.0001

Data Index: 291922 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0994. Min Act: -0.0001

Data Index: 113273 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0956. Min Act: -0.0001

Data Index: 986953 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1086664 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0919. Min Act: -0.0001

Data Index: 244639 (C4 (Web Text))

Max Activating Token Index: 881