Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1161 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.8926. Min Act: -0.0000

Data Index: 1256587 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.7767. Min Act: -0.0000

Data Index: 1276033 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.4996. Min Act: -0.0000

Data Index: 1065 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.7675. Min Act: -0.0000

Data Index: 627946 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.6562. Min Act: -0.0000

Data Index: 848271 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.6503. Min Act: -0.0000

Data Index: 562721 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.5980. Min Act: -0.0000

Data Index: 987795 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.5914. Min Act: -0.0000

Data Index: 420083 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.6640. Min Act: -0.0000

Data Index: 995167 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.6696. Min Act: -0.0000

Data Index: 586580 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.6242. Min Act: -0.0000

Data Index: 175823 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.5934. Min Act: -0.0000

Data Index: 1262735 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.5832. Min Act: -0.0000

Data Index: 548918 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.6663. Min Act: -0.0000

Data Index: 1082404 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.4923. Min Act: -0.0000

Data Index: 148277 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1036699 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.5667. Min Act: -0.0000

Data Index: 771286 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.4843. Min Act: -0.0000

Data Index: 572649 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.5451. Min Act: -0.0000

Data Index: 1121541 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.8926. Min Range: -1.8926

Max Act: 1.5106. Min Act: -0.0000

Data Index: 372213 (C4 (Web Text))

Max Activating Token Index: 785