Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2927 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9350. Min Act: -0.0001

Data Index: 765727 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8880. Min Act: -0.0001

Data Index: 279834 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8862. Min Act: -0.0001

Data Index: 282990 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8726. Min Act: -0.0001

Data Index: 352799 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9490. Min Act: -0.0001

Data Index: 45062 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.7802. Min Act: -0.0001

Data Index: 463952 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8022. Min Act: -0.0001

Data Index: 1050559 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8231. Min Act: -0.0001

Data Index: 480933 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.7294. Min Act: -0.0001

Data Index: 275654 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.0807. Min Range: -1.0807

Max Act: 1.0807. Min Act: -0.0001

Data Index: 665178 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8180. Min Act: -0.0001

Data Index: 1152184 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.7160. Min Act: -0.0001

Data Index: 508640 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8573. Min Act: -0.0001

Data Index: 991090 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9434. Min Act: -0.0001

Data Index: 1084294 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8393. Min Act: -0.0001

Data Index: 837357 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8130. Min Act: -0.0001

Data Index: 643462 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.7247. Min Act: -0.0001

Data Index: 332233 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.7748. Min Act: -0.0001

Data Index: 691393 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.7727. Min Act: -0.0001

Data Index: 645538 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8176. Min Act: -0.0001

Data Index: 13975 (C4 (Web Text))

Max Activating Token Index: 392