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

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

Neuron 4610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0120. Min Range: -5.0120

Max Act: 5.0120. Min Act: 0.0000

Data Index: 740783 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.9306. Min Act: 0.0000

Data Index: 532890 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.3673. Min Act: -0.0000

Data Index: 273033 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.4017. Min Act: -0.0000

Data Index: 132153 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.2943. Min Act: -0.0000

Data Index: 540696 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.3717. Min Act: 0.0000

Data Index: 833922 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.3513. Min Act: -0.0000

Data Index: 1263444 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.2314. Min Act: -0.0000

Data Index: 363699 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.5105. Min Act: -0.0000

Data Index: 413071 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.1890. Min Act: -0.0000

Data Index: 1169436 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.0117. Min Act: 0.0001

Data Index: 1301824 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 5.0120. Min Range: -5.0120

Max Act: 4.3042. Min Act: -0.0000

Data Index: 314884 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 5.0120. Min Range: -5.0120

Max Act: 3.9372. Min Act: 0.0001

Data Index: 743060 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 5.0120. Min Range: -5.0120

Max Act: 3.8135. Min Act: -0.0000

Data Index: 651430 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 5.0120. Min Range: -5.0120

Max Act: 3.8675. Min Act: -0.0000

Data Index: 59774 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 5.0120. Min Range: -5.0120

Max Act: 3.7013. Min Act: -0.0000

Data Index: 473326 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 5.0120. Min Range: -5.0120

Max Act: 3.7976. Min Act: -0.0000

Data Index: 122013 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 5.0120. Min Range: -5.0120

Max Act: 3.9754. Min Act: -0.0000

Data Index: 435689 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 5.0120. Min Range: -5.0120

Max Act: 3.6097. Min Act: -0.0000

Data Index: 470796 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 5.0120. Min Range: -5.0120

Max Act: 3.7630. Min Act: -0.0000

Data Index: 583249 (C4 (Web Text))

Max Activating Token Index: 667