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

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

Neuron 3570 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1907. Min Range: -1.1907

Max Act: 1.1907. Min Act: -0.0000

Data Index: 432611 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.1907. Min Range: -1.1907

Max Act: 1.1440. Min Act: -0.0000

Data Index: 530137 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.1907. Min Range: -1.1907

Max Act: 1.0614. Min Act: -0.0000

Data Index: 774452 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.1907. Min Range: -1.1907

Max Act: 1.0583. Min Act: -0.0000

Data Index: 412944 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.9638. Min Act: -0.0001

Data Index: 279745 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1010556 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1435514 (Python Code)

Max Activating Token Index: 790

Text #7

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1547586 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.6107. Min Act: -0.0000

Data Index: 495224 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.5916. Min Act: -0.0000

Data Index: 716902 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1088369 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.5764. Min Act: -0.0000

Data Index: 379046 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.5108. Min Act: -0.0000

Data Index: 471687 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.5193. Min Act: -0.0000

Data Index: 657799 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.4985. Min Act: -0.0000

Data Index: 276933 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.4900. Min Act: -0.0000

Data Index: 185455 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.5021. Min Act: -0.0000

Data Index: 81769 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1520935 (Python Code)

Max Activating Token Index: 460

Text #18

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.4793. Min Act: -0.0000

Data Index: 548452 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.1907. Min Range: -1.1907

Max Act: 0.4443. Min Act: -0.0000

Data Index: 815638 (C4 (Web Text))

Max Activating Token Index: 380