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

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

Neuron 457 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.9308. Min Act: -0.0000

Data Index: 222370 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 4.0111. Min Range: -4.0111

Max Act: 4.0111. Min Act: -0.0000

Data Index: 1273894 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.9874. Min Act: -0.0000

Data Index: 394675 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.4544. Min Act: -0.0000

Data Index: 132103 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.2963. Min Act: -0.0000

Data Index: 1240720 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.4624. Min Act: -0.0000

Data Index: 711376 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.3121. Min Act: -0.0000

Data Index: 805368 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.2747. Min Act: -0.0000

Data Index: 456157 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.1563. Min Act: -0.0000

Data Index: 194508 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.1587. Min Act: -0.0000

Data Index: 1008246 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.1201. Min Act: -0.0000

Data Index: 1339014 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.2499. Min Act: -0.0000

Data Index: 254501 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.0827. Min Act: -0.0000

Data Index: 1290491 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.0737. Min Act: -0.0000

Data Index: 1323735 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.9213. Min Act: -0.0000

Data Index: 1230372 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.0277. Min Act: -0.0000

Data Index: 1331632 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.0120. Min Act: -0.0000

Data Index: 676895 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.8008. Min Act: -0.0000

Data Index: 1177591 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.9569. Min Act: -0.0000

Data Index: 49306 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.8054. Min Act: -0.0000

Data Index: 367252 (C4 (Web Text))

Max Activating Token Index: 311