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

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

Neuron 3145 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7886. Min Act: -0.0000

Data Index: 703861 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1229357 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9378. Min Act: -0.0000

Data Index: 139055 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1213853 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9594. Min Act: -0.0000

Data Index: 976111 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1269403 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8447. Min Act: -0.0000

Data Index: 682009 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8714. Min Act: -0.0000

Data Index: 920179 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8639. Min Act: -0.0000

Data Index: 101432 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.9470. Min Act: -0.0000

Data Index: 599986 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1321156 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7996. Min Act: -0.0000

Data Index: 343716 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8638. Min Act: -0.0000

Data Index: 801375 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8378. Min Act: -0.0000

Data Index: 696153 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7739. Min Act: -0.0000

Data Index: 516613 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7624. Min Act: -0.0000

Data Index: 508999 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.8076. Min Act: -0.0000

Data Index: 237980 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7748. Min Act: -0.0000

Data Index: 424140 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7102. Min Act: -0.0000

Data Index: 149879 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.9594. Min Range: -0.9594

Max Act: 0.7382. Min Act: -0.0000

Data Index: 589155 (C4 (Web Text))

Max Activating Token Index: 749