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

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

Neuron 6 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: 7.9754. Min Range: -7.9754

Max Act: 7.9754. Min Act: -0.0000

Data Index: 157615 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 7.9754. Min Range: -7.9754

Max Act: 7.4733. Min Act: -0.0000

Data Index: 425916 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 7.9754. Min Range: -7.9754

Max Act: 7.7915. Min Act: -0.0000

Data Index: 1305157 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 7.9754. Min Range: -7.9754

Max Act: 6.2171. Min Act: -0.0000

Data Index: 785850 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 7.9754. Min Range: -7.9754

Max Act: 6.4235. Min Act: -0.0000

Data Index: 1350982 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.9325. Min Act: -0.0000

Data Index: 963607 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 7.9754. Min Range: -7.9754

Max Act: 6.0940. Min Act: -0.0000

Data Index: 665574 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 7.9754. Min Range: -7.9754

Max Act: 6.1568. Min Act: -0.0000

Data Index: 723939 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.9503. Min Act: -0.0000

Data Index: 549659 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 7.9754. Min Range: -7.9754

Max Act: 6.1323. Min Act: -0.0000

Data Index: 313736 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.5133. Min Act: -0.0000

Data Index: 1029690 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 7.9754. Min Range: -7.9754

Max Act: 6.6333. Min Act: -0.0000

Data Index: 1149086 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 7.9754. Min Range: -7.9754

Max Act: 6.1075. Min Act: -0.0000

Data Index: 254520 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.6542. Min Act: -0.0000

Data Index: 393164 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.9939. Min Act: -0.0000

Data Index: 1066257 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.7885. Min Act: -0.0000

Data Index: 252747 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.5271. Min Act: -0.0000

Data Index: 909850 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.8738. Min Act: -0.0000

Data Index: 738044 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 7.9754. Min Range: -7.9754

Max Act: 5.6372. Min Act: -0.0000

Data Index: 554284 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 7.9754. Min Range: -7.9754

Max Act: 6.0496. Min Act: -0.0000

Data Index: 675490 (C4 (Web Text))

Max Activating Token Index: 1017