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

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

Neuron 661 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0375. Min Range: -1.0375

Max Act: 1.0375. Min Act: -0.0001

Data Index: 479101 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.0375. Min Range: -1.0375

Max Act: 1.0006. Min Act: -0.0001

Data Index: 1081779 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.0375. Min Range: -1.0375

Max Act: 1.0005. Min Act: -0.0001

Data Index: 606824 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9499. Min Act: -0.0001

Data Index: 755809 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9690. Min Act: -0.0001

Data Index: 258036 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9214. Min Act: -0.0001

Data Index: 209055 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9214. Min Act: -0.0001

Data Index: 349947 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8587. Min Act: -0.0001

Data Index: 526853 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9219. Min Act: -0.0001

Data Index: 553957 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9090. Min Act: -0.0001

Data Index: 1332536 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9231. Min Act: -0.0001

Data Index: 922638 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9247. Min Act: -0.0001

Data Index: 473064 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8590. Min Act: -0.0001

Data Index: 956930 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8838. Min Act: -0.0001

Data Index: 134859 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9731. Min Act: -0.0001

Data Index: 669268 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8354. Min Act: -0.0001

Data Index: 1110359 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8342. Min Act: -0.0001

Data Index: 373618 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8649. Min Act: -0.0001

Data Index: 1605749 (Python Code)

Max Activating Token Index: 544

Text #18

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1001682 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8768. Min Act: -0.0001

Data Index: 994308 (C4 (Web Text))

Max Activating Token Index: 477