Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3677 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.7630. Min Range: -6.7630

Max Act: 6.7630. Min Act: -0.0000

Data Index: 896919 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 6.7630. Min Range: -6.7630

Max Act: 6.7476. Min Act: -0.0000

Data Index: 426202 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 6.7630. Min Range: -6.7630

Max Act: 6.5466. Min Act: -0.0000

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 6.7630. Min Range: -6.7630

Max Act: 6.4823. Min Act: -0.0000

Data Index: 586319 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 6.7630. Min Range: -6.7630

Max Act: 6.0182. Min Act: -0.0000

Data Index: 476925 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.9724. Min Act: -0.0000

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.8862. Min Act: -0.0000

Data Index: 1227805 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 6.7630. Min Range: -6.7630

Max Act: 6.1108. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.6855. Min Act: -0.0000

Data Index: 359936 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.6656. Min Act: -0.0000

Data Index: 840422 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.4661. Min Act: -0.0000

Data Index: 144390 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.6220. Min Act: -0.0000

Data Index: 707754 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.5481. Min Act: -0.0000

Data Index: 744405 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.4426. Min Act: -0.0000

Data Index: 337007 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.6121. Min Act: -0.0000

Data Index: 696290 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.3703. Min Act: -0.0000

Data Index: 705080 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.1778. Min Act: -0.0000

Data Index: 108785 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.5061. Min Act: -0.0000

Data Index: 83183 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.2921. Min Act: -0.0000

Data Index: 539015 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 6.7630. Min Range: -6.7630

Max Act: 5.2846. Min Act: -0.0000

Data Index: 660776 (C4 (Web Text))

Max Activating Token Index: 782