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

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

Neuron 2805 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.8729. Min Act: -0.0001

Data Index: 742184 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7368. Min Act: -0.0001

Data Index: 892230 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1225123 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7386. Min Act: -0.0001

Data Index: 1288952 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7694. Min Act: -0.0001

Data Index: 218097 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6792. Min Act: -0.0001

Data Index: 7820 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7459. Min Act: -0.0001

Data Index: 876534 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6660. Min Act: -0.0001

Data Index: 649830 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6474. Min Act: -0.0000

Data Index: 348830 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6652. Min Act: -0.0001

Data Index: 921583 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7492. Min Act: -0.0000

Data Index: 815387 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6952. Min Act: -0.0001

Data Index: 1148183 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6923. Min Act: -0.0001

Data Index: 1135839 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6463. Min Act: -0.0001

Data Index: 42658 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7494. Min Act: -0.0001

Data Index: 552361 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6079. Min Act: -0.0001

Data Index: 704595 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6626. Min Act: -0.0001

Data Index: 441144 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6646. Min Act: -0.0001

Data Index: 901272 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6574. Min Act: -0.0001

Data Index: 16068 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1030473 (C4 (Web Text))

Max Activating Token Index: 518