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

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

Neuron 3939 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: 1.0837. Min Range: -1.0837

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1345576 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.0837. Min Range: -1.0837

Max Act: 1.0427. Min Act: -0.0000

Data Index: 906681 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.0837. Min Range: -1.0837

Max Act: 1.0449. Min Act: -0.0000

Data Index: 191430 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.0837. Min Range: -1.0837

Max Act: 1.0015. Min Act: -0.0000

Data Index: 942586 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1008564 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 1.0837. Min Range: -1.0837

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1020261 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 1.0837. Min Range: -1.0837

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1309781 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1031433 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9161. Min Act: -0.0000

Data Index: 115594 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1057190 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8332. Min Act: -0.0000

Data Index: 607851 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.9134. Min Act: -0.0000

Data Index: 441236 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8814. Min Act: -0.0000

Data Index: 674137 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8714. Min Act: -0.0000

Data Index: 136067 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7941. Min Act: -0.0000

Data Index: 819474 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7704. Min Act: -0.0000

Data Index: 246601 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7660. Min Act: -0.0000

Data Index: 67818 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7586. Min Act: -0.0000

Data Index: 248558 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.7643. Min Act: -0.0000

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 1.0837. Min Range: -1.0837

Max Act: 0.8057. Min Act: -0.0000

Data Index: 148369 (C4 (Web Text))

Max Activating Token Index: 763