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

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

Neuron 4831 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1059052 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1135. Min Act: -0.0001

Data Index: 433494 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1085. Min Act: -0.0001

Data Index: 647543 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1107. Min Act: -0.0001

Data Index: 547713 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1078241 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0996. Min Act: -0.0001

Data Index: 559108 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0749. Min Act: -0.0001

Data Index: 613666 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1040660 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0864. Min Act: -0.0001

Data Index: 919912 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0830. Min Act: -0.0001

Data Index: 850915 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1298099 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1052667 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1362265 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0868. Min Act: -0.0001

Data Index: 416626 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0877. Min Act: -0.0001

Data Index: 469848 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1186083 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1076796 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1523516 (Python Code)

Max Activating Token Index: 694

Text #18

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0910. Min Act: -0.0001

Data Index: 707712 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1130016 (C4 (Web Text))

Max Activating Token Index: 972