Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5651 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.7389. Min Act: -0.0000

Data Index: 373064 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6908. Min Act: -0.0000

Data Index: 27312 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6808. Min Act: -0.0000

Data Index: 737984 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6767. Min Act: -0.0000

Data Index: 665653 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6199. Min Act: -0.0000

Data Index: 899032 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6103. Min Act: -0.0000

Data Index: 979625 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6285. Min Act: -0.0000

Data Index: 10158 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1084025 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1266197 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5522. Min Act: -0.0000

Data Index: 667734 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5280. Min Act: -0.0000

Data Index: 300494 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5713. Min Act: -0.0000

Data Index: 541196 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5544. Min Act: -0.0000

Data Index: 956916 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4985. Min Act: -0.0000

Data Index: 520771 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5470. Min Act: -0.0000

Data Index: 123651 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1145922 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1337516 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5282. Min Act: -0.0000

Data Index: 63187 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5260. Min Act: -0.0000

Data Index: 335585 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.7389. Min Range: -0.7389

Max Act: 0.5631. Min Act: -0.0000

Data Index: 599087 (C4 (Web Text))

Max Activating Token Index: 106