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

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

Neuron 4810 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0149. Min Range: -5.0149

Max Act: 5.0149. Min Act: -0.0000

Data Index: 669150 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 5.0149. Min Range: -5.0149

Max Act: 4.9394. Min Act: -0.0000

Data Index: 153581 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 5.0149. Min Range: -5.0149

Max Act: 4.5681. Min Act: -0.0000

Data Index: 660552 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 5.0149. Min Range: -5.0149

Max Act: 4.5204. Min Act: -0.0000

Data Index: 559800 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 5.0149. Min Range: -5.0149

Max Act: 4.2689. Min Act: -0.0000

Data Index: 595934 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 5.0149. Min Range: -5.0149

Max Act: 4.0860. Min Act: -0.0000

Data Index: 253648 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 5.0149. Min Range: -5.0149

Max Act: 3.4927. Min Act: -0.0000

Data Index: 356530 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.9899. Min Act: -0.0000

Data Index: 240011 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.8198. Min Act: -0.0000

Data Index: 1100708 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 5.0149. Min Range: -5.0149

Max Act: 3.0723. Min Act: -0.0000

Data Index: 700112 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.8914. Min Act: -0.0000

Data Index: 399043 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.8434. Min Act: -0.0000

Data Index: 153752 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.7278. Min Act: -0.0000

Data Index: 984507 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.5995. Min Act: -0.0000

Data Index: 1327559 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.5945. Min Act: -0.0000

Data Index: 167123 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.5806. Min Act: -0.0000

Data Index: 1007790 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.6322. Min Act: -0.0000

Data Index: 1017192 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.4767. Min Act: -0.0000

Data Index: 590096 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.4464. Min Act: -0.0000

Data Index: 297627 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 5.0149. Min Range: -5.0149

Max Act: 2.5626. Min Act: -0.0000

Data Index: 915123 (C4 (Web Text))

Max Activating Token Index: 925