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

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

Neuron 980 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1352060 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.2792. Min Act: -0.0000

Data Index: 79770 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.2724. Min Act: -0.0000

Data Index: 811233 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1260271 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.2685. Min Act: -0.0000

Data Index: 403156 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1949. Min Act: -0.0000

Data Index: 931800 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.2064. Min Act: -0.0000

Data Index: 850869 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.2186. Min Act: -0.0000

Data Index: 408483 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1929. Min Act: -0.0000

Data Index: 263231 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1536. Min Act: -0.0000

Data Index: 829289 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1297748 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1596. Min Act: -0.0000

Data Index: 746685 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.0868. Min Act: -0.0000

Data Index: 109766 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1840. Min Act: -0.0000

Data Index: 959356 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1586930 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1203. Min Act: -0.0000

Data Index: 942048 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1469. Min Act: -0.0000

Data Index: 940842 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.1060. Min Act: -0.0000

Data Index: 1178457 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.0993. Min Act: -0.0000

Data Index: 637428 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 1.4081. Min Range: -1.4081

Max Act: 1.0740. Min Act: -0.0000

Data Index: 1629722 (Python Code)

Max Activating Token Index: 121