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

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

Neuron 3982 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1587. Min Range: -1.1587

Max Act: 1.1587. Min Act: -0.0001

Data Index: 693222 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.9083. Min Act: -0.0000

Data Index: 824292 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.6515. Min Act: -0.0001

Data Index: 400266 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1135946 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1056763 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.5654. Min Act: -0.0001

Data Index: 206328 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4967. Min Act: -0.0000

Data Index: 330842 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4699. Min Act: -0.0000

Data Index: 699433 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.5011. Min Act: -0.0001

Data Index: 740020 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4663. Min Act: -0.0000

Data Index: 854686 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4945. Min Act: -0.0001

Data Index: 1263189 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1230095 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4615. Min Act: -0.0001

Data Index: 635299 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4823. Min Act: -0.0001

Data Index: 274547 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4486. Min Act: -0.0001

Data Index: 691476 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4914. Min Act: -0.0001

Data Index: 43733 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4915. Min Act: -0.0000

Data Index: 92118 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4606. Min Act: -0.0001

Data Index: 1184486 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4580. Min Act: -0.0000

Data Index: 385518 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.4167. Min Act: -0.0000

Data Index: 515378 (C4 (Web Text))

Max Activating Token Index: 962