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

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

Neuron 5001 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: 0.2552. Min Range: -0.2552

Max Act: 0.2552. Min Act: -0.0000

Data Index: 838805 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2128. Min Act: -0.0000

Data Index: 929134 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2186. Min Act: -0.0000

Data Index: 5812 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2062. Min Act: -0.0000

Data Index: 106486 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2094. Min Act: -0.0000

Data Index: 424784 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2013. Min Act: -0.0000

Data Index: 617701 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2227. Min Act: -0.0000

Data Index: 881713 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1227786 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2040. Min Act: -0.0000

Data Index: 787466 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2036. Min Act: -0.0000

Data Index: 114418 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2088. Min Act: -0.0000

Data Index: 272556 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1922. Min Act: -0.0001

Data Index: 328582 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1989. Min Act: -0.0001

Data Index: 297339 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1814. Min Act: -0.0000

Data Index: 554578 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1869. Min Act: -0.0000

Data Index: 478115 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1944. Min Act: -0.0000

Data Index: 709845 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1907. Min Act: -0.0000

Data Index: 612772 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1825. Min Act: -0.0000

Data Index: 588414 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1860. Min Act: -0.0000

Data Index: 46182 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1742. Min Act: -0.0000

Data Index: 502732 (C4 (Web Text))

Max Activating Token Index: 898