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

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

Neuron 1320 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1212. Min Act: -0.0001

Data Index: 509683 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1163. Min Act: -0.0001

Data Index: 970459 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1267497 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1136. Min Act: -0.0001

Data Index: 43626 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1007213 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1084. Min Act: -0.0000

Data Index: 755420 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1038. Min Act: -0.0001

Data Index: 947408 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1059. Min Act: -0.0001

Data Index: 930561 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1050. Min Act: -0.0001

Data Index: 734953 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1002. Min Act: -0.0000

Data Index: 678451 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0998. Min Act: -0.0000

Data Index: 588840 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1024. Min Act: -0.0001

Data Index: 350705 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1357687 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1013. Min Act: -0.0001

Data Index: 502566 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1001. Min Act: -0.0001

Data Index: 930915 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1027. Min Act: -0.0001

Data Index: 723029 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1301141 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1098046 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1137343 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0975. Min Act: -0.0001

Data Index: 783692 (C4 (Web Text))

Max Activating Token Index: 620