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

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

Neuron 1470 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: 0.5830. Min Range: -0.5830

Max Act: 0.5797. Min Act: -0.0002

Data Index: 403139 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5515. Min Act: -0.0002

Data Index: 1149490 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5463. Min Act: -0.0001

Data Index: 1139010 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5830. Min Act: -0.0001

Data Index: 342792 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5429. Min Act: -0.0001

Data Index: 281512 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5373. Min Act: -0.0001

Data Index: 1260518 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5228. Min Act: -0.0001

Data Index: 990806 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5357. Min Act: -0.0002

Data Index: 652623 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5409. Min Act: -0.0001

Data Index: 958909 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5070. Min Act: -0.0001

Data Index: 138070 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5321. Min Act: -0.0001

Data Index: 754780 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4491. Min Act: -0.0002

Data Index: 1225802 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4760. Min Act: -0.0001

Data Index: 1060096 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5103. Min Act: -0.0002

Data Index: 445566 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4977. Min Act: -0.0001

Data Index: 801589 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4917. Min Act: -0.0001

Data Index: 695854 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5087. Min Act: -0.0002

Data Index: 767451 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5062. Min Act: -0.0002

Data Index: 372454 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.5148. Min Act: -0.0001

Data Index: 566287 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.5830. Min Range: -0.5830

Max Act: 0.4860. Min Act: -0.0002

Data Index: 715837 (C4 (Web Text))

Max Activating Token Index: 529