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

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

Neuron 2727 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: 0.8619. Min Range: -0.8619

Max Act: 0.8303. Min Act: -0.0000

Data Index: 587777 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.8526. Min Act: -0.0000

Data Index: 221757 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.8619. Min Act: -0.0000

Data Index: 179016 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.8310. Min Act: -0.0000

Data Index: 143202 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7527. Min Act: -0.0000

Data Index: 411789 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1026358 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7727. Min Act: -0.0000

Data Index: 693591 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7223. Min Act: -0.0000

Data Index: 459146 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.6920. Min Act: -0.0000

Data Index: 688641 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.6843. Min Act: -0.0000

Data Index: 935584 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7008. Min Act: -0.0000

Data Index: 727914 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.6986. Min Act: -0.0000

Data Index: 966377 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7216. Min Act: -0.0000

Data Index: 592700 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1071755 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7145. Min Act: -0.0000

Data Index: 5814 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1200241 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.6677. Min Act: -0.0000

Data Index: 810137 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7050. Min Act: -0.0000

Data Index: 88370 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.6641. Min Act: -0.0000

Data Index: 356910 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.8619. Min Range: -0.8619

Max Act: 0.7002. Min Act: -0.0000

Data Index: 734909 (C4 (Web Text))

Max Activating Token Index: 776