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

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

Neuron 3859 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1080. Min Act: -0.0001

Data Index: 323299 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1052. Min Act: -0.0002

Data Index: 275851 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1035660 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1106. Min Act: -0.0001

Data Index: 485588 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1302207 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0978. Min Act: -0.0001

Data Index: 809033 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1243714 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0954. Min Act: -0.0001

Data Index: 578953 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1021. Min Act: -0.0002

Data Index: 256607 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1118704 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0915. Min Act: -0.0002

Data Index: 488799 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1093028 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1016958 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1227514 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0918. Min Act: -0.0002

Data Index: 265319 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1337072 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0951. Min Act: -0.0002

Data Index: 667105 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0969. Min Act: -0.0002

Data Index: 81878 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0868. Min Act: -0.0001

Data Index: 35047 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0900. Min Act: -0.0001

Data Index: 528952 (C4 (Web Text))

Max Activating Token Index: 729