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

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

Neuron 3899 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.9974. Min Act: -0.0000

Data Index: 587514 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8796. Min Act: -0.0001

Data Index: 1182643 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1240362 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1309385 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1211704 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1169539 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7948. Min Act: -0.0001

Data Index: 1321726 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8086. Min Act: -0.0001

Data Index: 979167 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7841. Min Act: -0.0001

Data Index: 1044659 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1241693 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.8093. Min Act: -0.0001

Data Index: 590374 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7282. Min Act: -0.0000

Data Index: 964189 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7688. Min Act: -0.0000

Data Index: 620996 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1157369 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7642. Min Act: -0.0001

Data Index: 385640 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1356530 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1025076 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7805. Min Act: -0.0000

Data Index: 585352 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7321. Min Act: -0.0001

Data Index: 239963 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.9974. Min Range: -0.9974

Max Act: 0.7546. Min Act: -0.0001

Data Index: 285607 (C4 (Web Text))

Max Activating Token Index: 701