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

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

Neuron 4509 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: 5.6768. Min Range: -5.6768

Max Act: 5.6768. Min Act: -0.0000

Data Index: 675652 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 5.6768. Min Range: -5.6768

Max Act: 5.4287. Min Act: -0.0001

Data Index: 1099563 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 5.6768. Min Range: -5.6768

Max Act: 5.2916. Min Act: -0.0000

Data Index: 799323 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 5.6768. Min Range: -5.6768

Max Act: 5.3903. Min Act: -0.0000

Data Index: 299431 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 5.6768. Min Range: -5.6768

Max Act: 5.2511. Min Act: -0.0001

Data Index: 1099828 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 5.6768. Min Range: -5.6768

Max Act: 5.0761. Min Act: -0.0001

Data Index: 493778 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.9938. Min Act: -0.0000

Data Index: 936634 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.8149. Min Act: -0.0000

Data Index: 1014247 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.9834. Min Act: -0.0001

Data Index: 218871 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.5195. Min Act: -0.0000

Data Index: 400825 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.4175. Min Act: -0.0000

Data Index: 1347364 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.8298. Min Act: -0.0001

Data Index: 881472 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.4381. Min Act: -0.0000

Data Index: 1035717 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.9175. Min Act: -0.0000

Data Index: 32584 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.4183. Min Act: -0.0001

Data Index: 1294305 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.0855. Min Act: -0.0000

Data Index: 1137050 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.4092. Min Act: -0.0001

Data Index: 674371 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.0487. Min Act: -0.0001

Data Index: 143748 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 5.6768. Min Range: -5.6768

Max Act: 4.1803. Min Act: -0.0001

Data Index: 70173 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 5.6768. Min Range: -5.6768

Max Act: 3.8211. Min Act: -0.0000

Data Index: 700545 (C4 (Web Text))

Max Activating Token Index: 728