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

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

Neuron 3968 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.2854. Min Act: -0.0001

Data Index: 747804 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.1558. Min Act: -0.0001

Data Index: 1154498 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.0841. Min Act: -0.0001

Data Index: 1353642 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.0644. Min Act: -0.0001

Data Index: 803046 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.0299. Min Act: -0.0001

Data Index: 1143596 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.0408. Min Act: -0.0001

Data Index: 1185484 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 1.2854. Min Range: -1.2854

Max Act: 1.0596. Min Act: -0.0001

Data Index: 1163846 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9692. Min Act: -0.0001

Data Index: 116580 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9628. Min Act: -0.0001

Data Index: 339251 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9651. Min Act: -0.0001

Data Index: 446011 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9522. Min Act: -0.0001

Data Index: 704345 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.8722. Min Act: -0.0001

Data Index: 949234 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9765. Min Act: -0.0001

Data Index: 1332918 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9245. Min Act: -0.0001

Data Index: 817641 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.8963. Min Act: -0.0001

Data Index: 830983 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9389. Min Act: -0.0001

Data Index: 244751 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9571. Min Act: -0.0001

Data Index: 1298710 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.8461. Min Act: -0.0001

Data Index: 936737 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9054. Min Act: -0.0001

Data Index: 716295 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 1.2854. Min Range: -1.2854

Max Act: 0.9083. Min Act: -0.0001

Data Index: 242595 (C4 (Web Text))

Max Activating Token Index: 546