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

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

Neuron 1387 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.8087. Min Act: -0.0000

Data Index: 708733 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.6856. Min Act: -0.0000

Data Index: 632203 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.4370. Min Act: -0.0000

Data Index: 896512 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.5218. Min Act: -0.0000

Data Index: 1054798 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.4148. Min Act: -0.0000

Data Index: 1164979 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.2782. Min Act: -0.0000

Data Index: 330396 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.3896. Min Act: -0.0000

Data Index: 534810 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.2467. Min Act: -0.0000

Data Index: 961876 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.3410. Min Act: -0.0000

Data Index: 1042293 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.1916. Min Act: -0.0000

Data Index: 1279071 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.3093. Min Act: -0.0000

Data Index: 890391 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.2550. Min Act: -0.0000

Data Index: 901649 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.2385. Min Act: -0.0000

Data Index: 778049 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.2515. Min Act: -0.0000

Data Index: 228796 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.1967. Min Act: -0.0000

Data Index: 249991 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.1759. Min Act: -0.0000

Data Index: 129637 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 2.8087. Min Range: -2.8087

Max Act: 2.2528. Min Act: -0.0000

Data Index: 196633 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 2.8087. Min Range: -2.8087

Max Act: 1.9425. Min Act: -0.0000

Data Index: 1101108 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 2.8087. Min Range: -2.8087

Max Act: 1.8633. Min Act: -0.0000

Data Index: 579072 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 2.8087. Min Range: -2.8087

Max Act: 1.7982. Min Act: -0.0000

Data Index: 1357536 (C4 (Web Text))

Max Activating Token Index: 496