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

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

Neuron 2186 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: 1.1417. Min Range: -1.1417

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1034484 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1050948 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1145564 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1557360 (Python Code)

Max Activating Token Index: 276

Text #4

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1127462 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1387775 (Python Code)

Max Activating Token Index: 734

Text #6

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8249. Min Act: -0.0000

Data Index: 834358 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8068. Min Act: -0.0000

Data Index: 126895 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.8143. Min Act: -0.0000

Data Index: 47045 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.7890. Min Act: -0.0000

Data Index: 536090 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.7509. Min Act: -0.0000

Data Index: 308840 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1135185 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.7625. Min Act: -0.0000

Data Index: 977698 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.6900. Min Act: -0.0000

Data Index: 638759 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.6894. Min Act: -0.0000

Data Index: 303272 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.7255. Min Act: -0.0000

Data Index: 528274 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1086182 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.6603. Min Act: -0.0000

Data Index: 794858 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.6673. Min Act: -0.0000

Data Index: 953474 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.1417. Min Range: -1.1417

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1088984 (C4 (Web Text))

Max Activating Token Index: 761