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

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

Neuron 5582 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.8258. Min Act: -0.0000

Data Index: 573042 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.5426. Min Act: -0.0000

Data Index: 580367 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.5380. Min Act: -0.0000

Data Index: 555911 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.6082. Min Act: -0.0000

Data Index: 677721 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.5138. Min Act: -0.0000

Data Index: 388145 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.4938. Min Act: -0.0000

Data Index: 820623 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.5925. Min Act: -0.0000

Data Index: 568280 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.3629. Min Act: -0.0000

Data Index: 500617 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.1202. Min Act: -0.0000

Data Index: 236399 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.3390. Min Act: -0.0000

Data Index: 1049330 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.4227. Min Act: -0.0000

Data Index: 861483 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.2687. Min Act: -0.0000

Data Index: 813559 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.3831. Min Act: -0.0000

Data Index: 882649 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.2077. Min Act: -0.0000

Data Index: 1027844 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.3762. Min Act: -0.0000

Data Index: 616026 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.0243. Min Act: -0.0000

Data Index: 943515 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.0224. Min Act: -0.0000

Data Index: 477132 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.1361. Min Act: -0.0000

Data Index: 625370 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.2292. Min Act: -0.0000

Data Index: 366493 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 2.8258. Min Range: -2.8258

Max Act: 2.0670. Min Act: -0.0000

Data Index: 544645 (C4 (Web Text))

Max Activating Token Index: 557