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

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

Neuron 3924 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7239. Min Act: -0.0000

Data Index: 133919 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1216659 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7162. Min Act: -0.0000

Data Index: 769605 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6750. Min Act: -0.0000

Data Index: 56801 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.7049. Min Act: -0.0000

Data Index: 709085 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6792. Min Act: -0.0000

Data Index: 401625 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1184214 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6581. Min Act: -0.0000

Data Index: 438514 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1126119 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6274. Min Act: -0.0000

Data Index: 309038 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5966. Min Act: -0.0000

Data Index: 569427 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6341. Min Act: -0.0000

Data Index: 495221 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6159. Min Act: -0.0000

Data Index: 768279 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1169242 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5887. Min Act: -0.0000

Data Index: 401170 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5845. Min Act: -0.0000

Data Index: 426277 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5958. Min Act: -0.0000

Data Index: 563974 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1322710 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1131965 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.7756. Min Range: -0.7756

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1299168 (C4 (Web Text))

Max Activating Token Index: 398