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

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

Neuron 3061 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: 1.8207. Min Range: -1.8207

Max Act: 1.7870. Min Act: -0.0001

Data Index: 337838 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.8207. Min Act: -0.0001

Data Index: 265721 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6622. Min Act: -0.0001

Data Index: 1267853 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6703. Min Act: -0.0001

Data Index: 755217 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7421. Min Act: -0.0001

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6207. Min Act: -0.0001

Data Index: 17906 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6787. Min Act: -0.0001

Data Index: 584774 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7535. Min Act: -0.0001

Data Index: 1212555 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7409. Min Act: -0.0001

Data Index: 698173 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6866. Min Act: -0.0001

Data Index: 551677 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7332. Min Act: -0.0001

Data Index: 1233490 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6974. Min Act: -0.0001

Data Index: 1283482 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6171. Min Act: -0.0001

Data Index: 319120 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.5760. Min Act: -0.0001

Data Index: 851475 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6023. Min Act: -0.0001

Data Index: 1044316 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6642. Min Act: -0.0001

Data Index: 518759 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7616. Min Act: -0.0001

Data Index: 771748 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.4619. Min Act: -0.0001

Data Index: 152154 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6513. Min Act: -0.0001

Data Index: 708803 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.5885. Min Act: -0.0001

Data Index: 852390 (C4 (Web Text))

Max Activating Token Index: 561