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

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

Neuron 4579 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2767. Min Act: -0.0000

Data Index: 81822 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2882. Min Act: -0.0000

Data Index: 75275 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1118803 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2331. Min Act: -0.0000

Data Index: 103144 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1172572 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2054. Min Act: -0.0000

Data Index: 625737 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1222307 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2066. Min Act: -0.0000

Data Index: 173730 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2070. Min Act: -0.0000

Data Index: 632848 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2128. Min Act: -0.0000

Data Index: 670595 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1238719 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1822. Min Act: -0.0000

Data Index: 30695 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2010. Min Act: -0.0000

Data Index: 458821 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1099978 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1904. Min Act: -0.0000

Data Index: 670907 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1128509 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1229263 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1035564 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1891. Min Act: -0.0000

Data Index: 478227 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1900. Min Act: -0.0000

Data Index: 981278 (C4 (Web Text))

Max Activating Token Index: 197