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

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

Neuron 2646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7799. Min Act: -0.0000

Data Index: 824964 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7107. Min Act: -0.0000

Data Index: 424550 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1132073 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6555. Min Act: -0.0000

Data Index: 574522 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1313260 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6498. Min Act: -0.0000

Data Index: 192482 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.7018. Min Act: -0.0000

Data Index: 994923 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6924. Min Act: -0.0000

Data Index: 48997 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1307424 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6689. Min Act: -0.0000

Data Index: 105140 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1177606 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6022. Min Act: -0.0000

Data Index: 473146 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6562. Min Act: -0.0000

Data Index: 928719 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6354. Min Act: -0.0000

Data Index: 344152 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1256886 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5905. Min Act: -0.0000

Data Index: 997768 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.6058. Min Act: -0.0000

Data Index: 348063 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1139042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5995. Min Act: -0.0000

Data Index: 535660 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.7799. Min Range: -0.7799

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1033067 (C4 (Web Text))

Max Activating Token Index: 962