Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 676 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2044. Min Range: -1.2044

Max Act: 1.2044. Min Act: -0.0000

Data Index: 136851 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 1.2044. Min Range: -1.2044

Max Act: 1.0907. Min Act: -0.0000

Data Index: 961953 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1243327 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.8038. Min Act: -0.0000

Data Index: 932506 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1140745 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1203715 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7364. Min Act: -0.0000

Data Index: 872415 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7668. Min Act: -0.0000

Data Index: 908015 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7572. Min Act: -0.0000

Data Index: 377182 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7065. Min Act: -0.0000

Data Index: 968066 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.6985. Min Act: 0.0000

Data Index: 1251741 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.6987. Min Act: -0.0000

Data Index: 798779 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7447. Min Act: -0.0000

Data Index: 436838 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.6926. Min Act: -0.0000

Data Index: 625107 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7748. Min Act: -0.0000

Data Index: 455144 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1332474 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1309235 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7168. Min Act: -0.0000

Data Index: 249074 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.7082. Min Act: -0.0000

Data Index: 544176 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.2044. Min Range: -1.2044

Max Act: 0.6619. Min Act: -0.0000

Data Index: 608798 (C4 (Web Text))

Max Activating Token Index: 400