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

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

Neuron 691 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.9390. Min Act: -0.0001

Data Index: 441554 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.8259. Min Act: -0.0002

Data Index: 962163 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.8845. Min Act: -0.0001

Data Index: 754204 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.8042. Min Act: -0.0001

Data Index: 607509 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7445. Min Act: -0.0001

Data Index: 131146 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7021. Min Act: -0.0001

Data Index: 632504 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.8125. Min Act: -0.0002

Data Index: 576649 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7841. Min Act: -0.0002

Data Index: 236114 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7088. Min Act: -0.0002

Data Index: 644730 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7476. Min Act: -0.0002

Data Index: 199127 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.6441. Min Act: -0.0001

Data Index: 166053 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7168. Min Act: -0.0001

Data Index: 810373 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.6862. Min Act: -0.0002

Data Index: 501184 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7303. Min Act: -0.0002

Data Index: 335183 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7538. Min Act: -0.0002

Data Index: 1131925 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.6785. Min Act: -0.0001

Data Index: 1131230 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7265. Min Act: -0.0002

Data Index: 314197 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.7096. Min Act: -0.0002

Data Index: 72334 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.6428. Min Act: -0.0002

Data Index: 1358385 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.9390. Min Range: -0.9390

Max Act: 0.6999. Min Act: -0.0001

Data Index: 629704 (C4 (Web Text))

Max Activating Token Index: 808