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

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

Neuron 4460 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1709. Min Range: -1.1709

Max Act: 1.1709. Min Act: -0.0000

Data Index: 1292564 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.1709. Min Range: -1.1709

Max Act: 1.0688. Min Act: -0.0000

Data Index: 815155 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.8959. Min Act: -0.0000

Data Index: 406642 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.9134. Min Act: -0.0000

Data Index: 927802 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1351101 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.8762. Min Act: -0.0000

Data Index: 941196 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.8320. Min Act: -0.0000

Data Index: 496572 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1545770 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.7496. Min Act: -0.0000

Data Index: 441620 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.7409. Min Act: -0.0000

Data Index: 823296 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.8003. Min Act: -0.0000

Data Index: 448867 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.7626. Min Act: -0.0000

Data Index: 387867 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.7298. Min Act: -0.0000

Data Index: 56181 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.6780. Min Act: -0.0000

Data Index: 270437 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.7711. Min Act: -0.0000

Data Index: 912686 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.7061. Min Act: -0.0000

Data Index: 394700 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1381417 (Python Code)

Max Activating Token Index: 318

Text #17

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.6769. Min Act: -0.0000

Data Index: 39541 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1563204 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 1.1709. Min Range: -1.1709

Max Act: 0.6663. Min Act: -0.0000

Data Index: 634121 (C4 (Web Text))

Max Activating Token Index: 442