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

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

Neuron 445 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5180. Min Range: -2.5180

Max Act: 2.5180. Min Act: -0.0000

Data Index: 688946 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 2.5180. Min Range: -2.5180

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1150919 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 2.5180. Min Range: -2.5180

Max Act: 1.1359. Min Act: -0.0000

Data Index: 109525 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.9755. Min Act: -0.0000

Data Index: 807680 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 2.5180. Min Range: -2.5180

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1121451 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.9663. Min Act: -0.0000

Data Index: 222849 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.9619. Min Act: -0.0000

Data Index: 578321 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1320518 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1317491 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.7164. Min Act: -0.0000

Data Index: 364601 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.7150. Min Act: -0.0000

Data Index: 568276 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.7253. Min Act: -0.0000

Data Index: 236669 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.6482. Min Act: -0.0000

Data Index: 60323 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.6870. Min Act: -0.0000

Data Index: 782616 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1335344 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.7343. Min Act: -0.0000

Data Index: 623320 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.6829. Min Act: -0.0000

Data Index: 315316 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.6686. Min Act: -0.0000

Data Index: 416343 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1279321 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 2.5180. Min Range: -2.5180

Max Act: 0.6613. Min Act: -0.0000

Data Index: 714232 (C4 (Web Text))

Max Activating Token Index: 1011