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

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

Neuron 3115 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: 1.3708. Min Range: -1.3708

Max Act: 1.3708. Min Act: -0.0001

Data Index: 1205383 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.3311. Min Act: -0.0001

Data Index: 1200835 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2027. Min Act: -0.0001

Data Index: 779944 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1915. Min Act: -0.0001

Data Index: 160519 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2242. Min Act: -0.0001

Data Index: 569516 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0946. Min Act: -0.0001

Data Index: 134674 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1323. Min Act: -0.0001

Data Index: 1185798 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0959. Min Act: -0.0001

Data Index: 774943 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1217. Min Act: -0.0001

Data Index: 808046 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0798. Min Act: -0.0001

Data Index: 142958 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0638. Min Act: -0.0001

Data Index: 414958 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0046. Min Act: -0.0001

Data Index: 907787 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2341. Min Act: -0.0001

Data Index: 1012946 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0267. Min Act: -0.0001

Data Index: 1157421 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0767. Min Act: -0.0001

Data Index: 536524 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1099. Min Act: -0.0001

Data Index: 1160108 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9516. Min Act: -0.0001

Data Index: 1048766 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9804. Min Act: -0.0001

Data Index: 1087475 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0155. Min Act: -0.0001

Data Index: 1208238 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0434. Min Act: -0.0001

Data Index: 871021 (C4 (Web Text))

Max Activating Token Index: 826