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

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

Neuron 2801 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: 0.2657. Min Range: -0.2657

Max Act: 0.2657. Min Act: -0.0000

Data Index: 47192 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2563. Min Act: -0.0000

Data Index: 821284 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2193. Min Act: -0.0000

Data Index: 532697 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2208. Min Act: -0.0000

Data Index: 67026 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2091. Min Act: -0.0000

Data Index: 590238 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2004. Min Act: -0.0000

Data Index: 800691 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1324541 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1957. Min Act: -0.0000

Data Index: 845181 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1154343 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2032. Min Act: -0.0000

Data Index: 286034 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2020. Min Act: -0.0000

Data Index: 459316 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1880. Min Act: -0.0000

Data Index: 107268 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1995. Min Act: -0.0000

Data Index: 9356 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1925. Min Act: -0.0000

Data Index: 727778 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1839. Min Act: -0.0000

Data Index: 228953 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1899. Min Act: -0.0000

Data Index: 96280 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1847. Min Act: -0.0000

Data Index: 828461 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1971. Min Act: -0.0000

Data Index: 271785 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1898. Min Act: -0.0000

Data Index: 471016 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1835. Min Act: -0.0000

Data Index: 385984 (C4 (Web Text))

Max Activating Token Index: 7