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

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

Neuron 3200 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: 0.2458. Min Range: -0.2458

Max Act: 0.2268. Min Act: -0.0000

Data Index: 916029 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2110. Min Act: -0.0000

Data Index: 896758 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1198399 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2458. Min Act: -0.0000

Data Index: 773189 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2223. Min Act: -0.0000

Data Index: 838256 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2213. Min Act: -0.0000

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2199. Min Act: -0.0000

Data Index: 888212 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2111. Min Act: -0.0000

Data Index: 56916 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1063169 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2015. Min Act: -0.0000

Data Index: 611418 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1212389 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1983. Min Act: -0.0000

Data Index: 446295 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2058. Min Act: -0.0000

Data Index: 775006 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1296401 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1134655 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1797. Min Act: -0.0000

Data Index: 789260 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2008. Min Act: -0.0000

Data Index: 334519 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1101923 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1851. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1860. Min Act: -0.0000

Data Index: 392136 (C4 (Web Text))

Max Activating Token Index: 814