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

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

Neuron 3551 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.3554. Min Act: -0.0001

Data Index: 481187 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.1468. Min Act: -0.0001

Data Index: 751239 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.1116. Min Act: -0.0001

Data Index: 1304746 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.1844. Min Act: -0.0001

Data Index: 982954 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.1733. Min Act: -0.0001

Data Index: 293950 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0967. Min Act: -0.0002

Data Index: 233112 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.1514. Min Act: -0.0001

Data Index: 81449 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.1403. Min Act: -0.0002

Data Index: 1089981 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0632. Min Act: -0.0002

Data Index: 764547 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0271. Min Act: -0.0002

Data Index: 933738 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0651. Min Act: -0.0001

Data Index: 781462 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.1260. Min Act: -0.0001

Data Index: 363985 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0840. Min Act: -0.0002

Data Index: 791833 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0587. Min Act: -0.0002

Data Index: 287183 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0542. Min Act: -0.0001

Data Index: 424475 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0695. Min Act: -0.0001

Data Index: 425237 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0297. Min Act: -0.0001

Data Index: 10020 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0012. Min Act: -0.0002

Data Index: 630043 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0769. Min Act: -0.0001

Data Index: 475404 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.3554. Min Range: -1.3554

Max Act: 1.0884. Min Act: -0.0002

Data Index: 725453 (C4 (Web Text))

Max Activating Token Index: 1003