Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2285 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1214. Min Act: -0.0000

Data Index: 14634 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1307268 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1230929 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1102513 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1035. Min Act: -0.0000

Data Index: 595392 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1145872 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1288600 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1052. Min Act: -0.0000

Data Index: 455668 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1249795 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1083. Min Act: -0.0000

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1038. Min Act: -0.0000

Data Index: 332948 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1019. Min Act: -0.0000

Data Index: 387954 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0941. Min Act: -0.0000

Data Index: 471335 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1024. Min Act: -0.0000

Data Index: 762142 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0996. Min Act: -0.0000

Data Index: 687267 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1028. Min Act: -0.0000

Data Index: 450175 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1116697 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1025. Min Act: -0.0000

Data Index: 80086 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0944. Min Act: -0.0000

Data Index: 148103 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0972. Min Act: -0.0000

Data Index: 718964 (C4 (Web Text))

Max Activating Token Index: 854