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

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

Neuron 2635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.6603. Min Act: -0.0000

Data Index: 275027 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.5961. Min Act: -0.0000

Data Index: 392483 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.3571. Min Act: -0.0000

Data Index: 471296 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.4040. Min Act: -0.0000

Data Index: 568753 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.4815. Min Act: -0.0000

Data Index: 1092889 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2760. Min Act: -0.0000

Data Index: 660184 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.3576. Min Act: -0.0000

Data Index: 1091475 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2690. Min Act: -0.0000

Data Index: 928479 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2421. Min Act: -0.0000

Data Index: 824852 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2959. Min Act: -0.0000

Data Index: 698746 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.3575. Min Act: -0.0000

Data Index: 143344 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2669. Min Act: -0.0000

Data Index: 771814 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2678. Min Act: -0.0000

Data Index: 368609 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2280. Min Act: -0.0000

Data Index: 640886 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.1527. Min Act: -0.0000

Data Index: 750300 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1327469 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1239382 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2620. Min Act: -0.0000

Data Index: 143772 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.1802. Min Act: -0.0000

Data Index: 838164 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 1.6603. Min Range: -1.6603

Max Act: 1.2452. Min Act: -0.0000

Data Index: 464792 (C4 (Web Text))

Max Activating Token Index: 511