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

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

Neuron 4339 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.3164. Min Act: 0.0000

Data Index: 630900 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2592. Min Act: -0.0000

Data Index: 822385 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2598. Min Act: -0.0000

Data Index: 598228 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2545. Min Act: -0.0000

Data Index: 215797 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2362. Min Act: -0.0000

Data Index: 846677 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2427. Min Act: -0.0000

Data Index: 816010 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2368. Min Act: -0.0000

Data Index: 850312 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1170535 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1178018 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1004758 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2016. Min Act: 0.0000

Data Index: 390578 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.2003. Min Act: -0.0000

Data Index: 58796 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1208375 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.1819. Min Act: -0.0000

Data Index: 222692 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.1860. Min Act: -0.0000

Data Index: 864286 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1632009 (Python Code)

Max Activating Token Index: 97

Text #16

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1106500 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1628326 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1222244 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.3164. Min Range: -0.3164

Max Act: 0.1744. Min Act: -0.0000

Data Index: 590354 (C4 (Web Text))

Max Activating Token Index: 887