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

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

Neuron 1661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4441. Min Act: -0.0001

Data Index: 202107 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4234. Min Act: -0.0001

Data Index: 657255 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3963. Min Act: -0.0001

Data Index: 378269 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3892. Min Act: -0.0001

Data Index: 607862 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4301. Min Act: -0.0001

Data Index: 811372 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3906. Min Act: -0.0001

Data Index: 440431 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3854. Min Act: -0.0001

Data Index: 980279 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3568. Min Act: -0.0001

Data Index: 1285007 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3487. Min Act: -0.0001

Data Index: 1103397 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3366. Min Act: -0.0001

Data Index: 443561 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3312. Min Act: -0.0001

Data Index: 301780 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3397. Min Act: -0.0001

Data Index: 1056967 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3172. Min Act: -0.0001

Data Index: 1330581 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3001. Min Act: -0.0001

Data Index: 842342 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3390. Min Act: -0.0001

Data Index: 525851 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3121. Min Act: -0.0001

Data Index: 651498 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2993. Min Act: -0.0001

Data Index: 1028401 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3316. Min Act: -0.0001

Data Index: 529540 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3014. Min Act: -0.0001

Data Index: 1097735 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3006. Min Act: -0.0001

Data Index: 39249 (C4 (Web Text))

Max Activating Token Index: 38