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

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

Neuron 3397 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: 0.1312. Min Range: -0.1312

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1208980 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1195. Min Act: -0.0001

Data Index: 239573 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1118. Min Act: -0.0001

Data Index: 862326 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1192. Min Act: -0.0001

Data Index: 640849 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1100671 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1016173 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1138. Min Act: -0.0001

Data Index: 765856 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1070. Min Act: -0.0001

Data Index: 464235 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0984. Min Act: -0.0001

Data Index: 161258 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1066. Min Act: -0.0001

Data Index: 87658 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1059. Min Act: -0.0001

Data Index: 575714 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1063. Min Act: -0.0001

Data Index: 410896 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1025. Min Act: -0.0001

Data Index: 169205 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1049. Min Act: -0.0001

Data Index: 172635 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1050. Min Act: -0.0001

Data Index: 791184 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1162008 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1044. Min Act: -0.0001

Data Index: 866930 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1080. Min Act: -0.0001

Data Index: 590603 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0995. Min Act: -0.0001

Data Index: 863117 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1252117 (C4 (Web Text))

Max Activating Token Index: 558