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

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

Neuron 2790 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6501. Min Act: -0.0000

Data Index: 15442 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4394. Min Act: -0.0000

Data Index: 986600 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4365. Min Act: -0.0000

Data Index: 714853 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3779. Min Act: -0.0000

Data Index: 402816 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4008. Min Act: -0.0000

Data Index: 956001 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1160569 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3652. Min Act: -0.0000

Data Index: 722802 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3433. Min Act: -0.0000

Data Index: 397386 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3566. Min Act: -0.0000

Data Index: 159173 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1210825 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3548. Min Act: -0.0000

Data Index: 376728 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1106725 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3155. Min Act: -0.0000

Data Index: 931352 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3276. Min Act: -0.0000

Data Index: 538775 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3634. Min Act: -0.0000

Data Index: 635458 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3252. Min Act: -0.0000

Data Index: 208008 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3157. Min Act: -0.0000

Data Index: 992048 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3226. Min Act: -0.0000

Data Index: 683965 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1211783 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1203217 (C4 (Web Text))

Max Activating Token Index: 438