Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2765 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6760. Min Act: -0.0000

Data Index: 157711 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1160128 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1317095 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1003719 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6018. Min Act: -0.0000

Data Index: 606632 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6335. Min Act: -0.0001

Data Index: 1116212 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6287. Min Act: -0.0000

Data Index: 566925 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1245727 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5867. Min Act: -0.0000

Data Index: 256868 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6251. Min Act: -0.0000

Data Index: 940066 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5898. Min Act: -0.0000

Data Index: 886549 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6182. Min Act: -0.0000

Data Index: 973709 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5877. Min Act: -0.0001

Data Index: 772557 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5383. Min Act: -0.0001

Data Index: 68743 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1008407 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5655. Min Act: -0.0000

Data Index: 681439 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5425. Min Act: -0.0001

Data Index: 615991 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5478. Min Act: -0.0000

Data Index: 39398 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5321. Min Act: -0.0000

Data Index: 13991 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5519. Min Act: -0.0000

Data Index: 907756 (C4 (Web Text))

Max Activating Token Index: 879