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

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

Neuron 2500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3934. Min Range: -3.3934

Max Act: 3.3934. Min Act: -0.0000

Data Index: 1150870 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.5205. Min Act: -0.0000

Data Index: 609248 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.6061. Min Act: -0.0000

Data Index: 594862 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.3606. Min Act: -0.0000

Data Index: 983858 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.4224. Min Act: -0.0000

Data Index: 1160856 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.3794. Min Act: -0.0000

Data Index: 4072 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.1882. Min Act: -0.0000

Data Index: 690141 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.3550. Min Act: -0.0000

Data Index: 1252608 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.2084. Min Act: -0.0000

Data Index: 870887 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.0754. Min Act: -0.0000

Data Index: 290261 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1213201 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.0492. Min Act: -0.0000

Data Index: 635964 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 3.3934. Min Range: -3.3934

Max Act: 2.0345. Min Act: -0.0000

Data Index: 891034 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 3.3934. Min Range: -3.3934

Max Act: 1.9781. Min Act: -0.0000

Data Index: 631668 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 3.3934. Min Range: -3.3934

Max Act: 1.7496. Min Act: -0.0000

Data Index: 180099 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.3934. Min Range: -3.3934

Max Act: 1.8742. Min Act: -0.0001

Data Index: 165182 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 3.3934. Min Range: -3.3934

Max Act: 1.9437. Min Act: -0.0000

Data Index: 1115196 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 3.3934. Min Range: -3.3934

Max Act: 1.8582. Min Act: -0.0001

Data Index: 136431 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 3.3934. Min Range: -3.3934

Max Act: 1.8560. Min Act: -0.0000

Data Index: 87093 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 3.3934. Min Range: -3.3934

Max Act: 1.7433. Min Act: -0.0000

Data Index: 155424 (C4 (Web Text))

Max Activating Token Index: 249