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

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

Neuron 1495 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2686. Min Act: -0.0000

Data Index: 232102 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2135. Min Act: -0.0000

Data Index: 131216 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2112. Min Act: -0.0000

Data Index: 724521 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2046. Min Act: -0.0000

Data Index: 426027 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1169879 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1012644 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1908. Min Act: -0.0000

Data Index: 230752 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1883. Min Act: -0.0000

Data Index: 569078 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1969. Min Act: -0.0000

Data Index: 114808 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1700. Min Act: -0.0000

Data Index: 525970 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1308719 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1819. Min Act: -0.0000

Data Index: 408820 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1266850 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1278675 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1787. Min Act: -0.0000

Data Index: 900273 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1348313 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1784. Min Act: -0.0000

Data Index: 929463 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1762. Min Act: -0.0000

Data Index: 103113 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1650. Min Act: -0.0000

Data Index: 257735 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1816. Min Act: -0.0000

Data Index: 262949 (C4 (Web Text))

Max Activating Token Index: 241