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

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

Neuron 726 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9932. Min Act: -0.0000

Data Index: 220555 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9538. Min Act: -0.0000

Data Index: 705341 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1148844 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8929. Min Act: -0.0000

Data Index: 536502 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9090. Min Act: -0.0000

Data Index: 991526 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9014. Min Act: -0.0000

Data Index: 760725 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8677. Min Act: -0.0000

Data Index: 142946 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8239. Min Act: -0.0000

Data Index: 69518 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1005456 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7983. Min Act: -0.0000

Data Index: 494638 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7725. Min Act: -0.0000

Data Index: 503787 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7880. Min Act: -0.0000

Data Index: 929003 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1025708 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1041133 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7265. Min Act: -0.0000

Data Index: 171507 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.6931. Min Act: -0.0000

Data Index: 918112 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7276. Min Act: -0.0000

Data Index: 875971 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7672. Min Act: -0.0000

Data Index: 989047 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7195. Min Act: -0.0000

Data Index: 962840 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1064643 (C4 (Web Text))

Max Activating Token Index: 881