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

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

Neuron 3349 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7540. Min Range: -6.7540

Max Act: 6.7540. Min Act: -0.0000

Data Index: 228441 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.9154. Min Act: -0.0000

Data Index: 1029561 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.7106. Min Act: -0.0000

Data Index: 623013 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.7442. Min Act: -0.0000

Data Index: 1168706 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.1471. Min Act: -0.0000

Data Index: 1029217 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.3063. Min Act: -0.0000

Data Index: 377261 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.5023. Min Act: -0.0000

Data Index: 1223847 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.6515. Min Act: -0.0000

Data Index: 859004 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.6275. Min Act: -0.0000

Data Index: 260235 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.4546. Min Act: -0.0000

Data Index: 1206831 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.3889. Min Act: -0.0000

Data Index: 69142 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.7930. Min Act: -0.0000

Data Index: 1062547 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.1563. Min Act: -0.0000

Data Index: 921638 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.5052. Min Act: -0.0000

Data Index: 1337005 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.3114. Min Act: -0.0000

Data Index: 345179 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.2815. Min Act: -0.0000

Data Index: 40566 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.2234. Min Act: -0.0000

Data Index: 116689 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 6.7540. Min Range: -6.7540

Max Act: 4.9501. Min Act: -0.0000

Data Index: 400948 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 6.7540. Min Range: -6.7540

Max Act: 4.9319. Min Act: -0.0000

Data Index: 784636 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 6.7540. Min Range: -6.7540

Max Act: 5.1014. Min Act: -0.0000

Data Index: 603744 (C4 (Web Text))

Max Activating Token Index: 846