Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2188 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1889. Min Act: -0.0000

Data Index: 902736 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0451. Min Act: -0.0001

Data Index: 1374009 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.9185. Min Act: -0.0001

Data Index: 1225330 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.9057. Min Act: -0.0000

Data Index: 360953 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.9108. Min Act: -0.0000

Data Index: 228931 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.8762. Min Act: -0.0001

Data Index: 1395989 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7917. Min Act: -0.0000

Data Index: 226007 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1545737 (Python Code)

Max Activating Token Index: 612

Text #8

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1206632 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7815. Min Act: -0.0000

Data Index: 86001 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1061697 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7644. Min Act: -0.0000

Data Index: 712497 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1175365 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7769. Min Act: -0.0000

Data Index: 661147 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7677. Min Act: -0.0001

Data Index: 1284475 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1591749 (Python Code)

Max Activating Token Index: 483

Text #16

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.6698. Min Act: 0.0000

Data Index: 124011 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1096720 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.7014. Min Act: -0.0000

Data Index: 257699 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.6783. Min Act: -0.0000

Data Index: 916231 (C4 (Web Text))

Max Activating Token Index: 449