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

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

Neuron 2678 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1850. Min Act: -0.0001

Data Index: 70126 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1929. Min Act: -0.0001

Data Index: 536926 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1719. Min Act: -0.0001

Data Index: 354438 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1341144 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1541. Min Act: -0.0001

Data Index: 674996 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1718. Min Act: -0.0000

Data Index: 971630 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1746. Min Act: -0.0001

Data Index: 478080 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1735. Min Act: -0.0001

Data Index: 594408 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1151796 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1666. Min Act: -0.0001

Data Index: 482576 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1689. Min Act: -0.0001

Data Index: 701698 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1663. Min Act: -0.0001

Data Index: 13441 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1617. Min Act: -0.0000

Data Index: 81865 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1662. Min Act: -0.0001

Data Index: 902679 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1318796 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1478. Min Act: -0.0000

Data Index: 316895 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1589. Min Act: -0.0001

Data Index: 152241 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1502. Min Act: -0.0001

Data Index: 290519 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1563. Min Act: -0.0001

Data Index: 430237 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1337959 (C4 (Web Text))

Max Activating Token Index: 582