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

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

Neuron 3424 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1773. Min Act: -0.0001

Data Index: 278708 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1605. Min Act: -0.0001

Data Index: 807360 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1007. Min Act: -0.0001

Data Index: 177821 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1277. Min Act: -0.0001

Data Index: 331977 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.2159. Min Act: -0.0001

Data Index: 829891 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1839. Min Act: -0.0001

Data Index: 1114702 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1404. Min Act: -0.0001

Data Index: 1071143 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0639. Min Act: -0.0001

Data Index: 1351910 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1175. Min Act: -0.0001

Data Index: 67544 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1484. Min Act: -0.0001

Data Index: 910114 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0768. Min Act: -0.0001

Data Index: 769513 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0684. Min Act: -0.0001

Data Index: 1286326 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0338. Min Act: -0.0001

Data Index: 329240 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0441. Min Act: -0.0001

Data Index: 207029 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0401. Min Act: -0.0001

Data Index: 789970 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.1007. Min Act: -0.0001

Data Index: 494700 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0952. Min Act: -0.0001

Data Index: 1145048 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0540. Min Act: -0.0001

Data Index: 810590 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0016. Min Act: -0.0001

Data Index: 634816 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0906. Min Act: -0.0001

Data Index: 412585 (C4 (Web Text))

Max Activating Token Index: 900