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

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

Neuron 2867 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.9454. Min Act: -0.0000

Data Index: 593272 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.5146. Min Act: -0.0001

Data Index: 16972 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.6569. Min Act: -0.0001

Data Index: 841681 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.3651. Min Act: -0.0001

Data Index: 48352 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.2677. Min Act: -0.0001

Data Index: 365401 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.2621. Min Act: -0.0001

Data Index: 1280083 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.3130. Min Act: -0.0001

Data Index: 486654 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.2385. Min Act: -0.0001

Data Index: 1241537 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.2614. Min Act: -0.0001

Data Index: 382948 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1074085 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.0436. Min Act: -0.0000

Data Index: 492199 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.2441. Min Act: -0.0001

Data Index: 322628 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.0973. Min Act: -0.0000

Data Index: 746043 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.1229. Min Act: -0.0001

Data Index: 691902 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.1385. Min Act: -0.0001

Data Index: 606909 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.1733. Min Act: -0.0001

Data Index: 225103 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.1809. Min Act: -0.0001

Data Index: 134471 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.2292. Min Act: -0.0000

Data Index: 524701 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.0879. Min Act: -0.0001

Data Index: 1016923 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 1.9454. Min Range: -1.9454

Max Act: 1.0601. Min Act: -0.0000

Data Index: 277010 (C4 (Web Text))

Max Activating Token Index: 477