Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 371 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0768. Min Act: -0.0001

Data Index: 355665 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0001

Data Index: 897042 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0702. Min Act: -0.0001

Data Index: 779497 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0737. Min Act: -0.0001

Data Index: 459219 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1189971 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1511698 (Python Code)

Max Activating Token Index: 317

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0631. Min Act: -0.0001

Data Index: 33550 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0700. Min Act: -0.0001

Data Index: 836561 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1219270 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0626. Min Act: -0.0001

Data Index: 209600 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1105032 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0693. Min Act: -0.0001

Data Index: 531670 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0644. Min Act: -0.0001

Data Index: 182762 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0665. Min Act: -0.0001

Data Index: 395397 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0735. Min Act: -0.0001

Data Index: 722505 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1149479 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0638. Min Act: -0.0001

Data Index: 571819 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0629. Min Act: -0.0001

Data Index: 25471 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1079263 (C4 (Web Text))

Max Activating Token Index: 161