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

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

Neuron 4678 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.9382. Min Act: 0.0000

Data Index: 376358 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.9053. Min Act: -0.0000

Data Index: 1182528 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.7465. Min Act: -0.0000

Data Index: 744363 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.4996. Min Act: -0.0000

Data Index: 312927 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.6203. Min Act: -0.0000

Data Index: 598256 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.7258. Min Act: 0.0000

Data Index: 222471 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.4690. Min Act: -0.0000

Data Index: 744542 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.4471. Min Act: -0.0000

Data Index: 785039 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.4039. Min Act: -0.0000

Data Index: 696669 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.5377. Min Act: 0.0000

Data Index: 1040763 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.5240. Min Act: -0.0000

Data Index: 476261 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.3564. Min Act: -0.0000

Data Index: 1153077 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.3086. Min Act: 0.0000

Data Index: 604467 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.3774. Min Act: -0.0000

Data Index: 483429 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 2.9382. Min Range: -2.9382

Max Act: 2.1569. Min Act: -0.0000

Data Index: 1158184 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 2.9382. Min Range: -2.9382

Max Act: 1.2833. Min Act: -0.0000

Data Index: 593483 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 2.9382. Min Range: -2.9382

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1164207 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 2.9382. Min Range: -2.9382

Max Act: 0.9513. Min Act: 0.0000

Data Index: 1538765 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 2.9382. Min Range: -2.9382

Max Act: 0.9718. Min Act: -0.0000

Data Index: 957810 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 2.9382. Min Range: -2.9382

Max Act: 0.8816. Min Act: -0.0000

Data Index: 529073 (C4 (Web Text))

Max Activating Token Index: 410