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

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

Neuron 3591 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: 2.5381. Min Range: -2.5381

Max Act: 2.2890. Min Act: -0.0000

Data Index: 957576 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 2.5381. Min Range: -2.5381

Max Act: 2.5381. Min Act: -0.0000

Data Index: 504959 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 2.5381. Min Range: -2.5381

Max Act: 2.3535. Min Act: -0.0000

Data Index: 1145964 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.9922. Min Act: -0.0000

Data Index: 866812 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 2.5381. Min Range: -2.5381

Max Act: 2.1780. Min Act: -0.0000

Data Index: 659388 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.9427. Min Act: -0.0000

Data Index: 87709 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 2.5381. Min Range: -2.5381

Max Act: 2.0388. Min Act: -0.0000

Data Index: 1084680 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.8946. Min Act: -0.0000

Data Index: 22082 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 2.5381. Min Range: -2.5381

Max Act: 2.0892. Min Act: -0.0000

Data Index: 1191831 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 2.5381. Min Range: -2.5381

Max Act: 2.0117. Min Act: -0.0000

Data Index: 849588 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.9336. Min Act: -0.0000

Data Index: 1151558 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.9749. Min Act: -0.0000

Data Index: 1262662 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.8526. Min Act: -0.0000

Data Index: 1021562 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.8779. Min Act: -0.0000

Data Index: 731268 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.7454. Min Act: -0.0000

Data Index: 313621 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.8656. Min Act: -0.0000

Data Index: 679694 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.7663. Min Act: -0.0000

Data Index: 1206425 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.7359. Min Act: -0.0000

Data Index: 1189047 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.7275. Min Act: -0.0000

Data Index: 50648 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 2.5381. Min Range: -2.5381

Max Act: 1.9286. Min Act: -0.0000

Data Index: 45594 (C4 (Web Text))

Max Activating Token Index: 793