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

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

Neuron 4510 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4309. Min Range: -6.4309

Max Act: 6.4309. Min Act: -0.0001

Data Index: 915109 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 6.4309. Min Range: -6.4309

Max Act: 6.0403. Min Act: -0.0001

Data Index: 41510 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.4080. Min Act: -0.0000

Data Index: 488069 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.9456. Min Act: -0.0001

Data Index: 1280586 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.2841. Min Act: -0.0000

Data Index: 31108 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.8573. Min Act: -0.0001

Data Index: 160418 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.7077. Min Act: -0.0001

Data Index: 1172358 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.2169. Min Act: -0.0001

Data Index: 932352 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.5826. Min Act: -0.0001

Data Index: 508983 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.5775. Min Act: -0.0001

Data Index: 111356 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.8991. Min Act: -0.0001

Data Index: 628070 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.3717. Min Act: -0.0000

Data Index: 209890 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.6559. Min Act: -0.0001

Data Index: 587980 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.1408. Min Act: -0.0001

Data Index: 157757 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.5600. Min Act: -0.0001

Data Index: 767724 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 6.4309. Min Range: -6.4309

Max Act: 4.6330. Min Act: -0.0001

Data Index: 1042947 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.4665. Min Act: -0.0000

Data Index: 837450 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.0910. Min Act: -0.0000

Data Index: 1358328 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 6.4309. Min Range: -6.4309

Max Act: 5.1020. Min Act: -0.0001

Data Index: 74802 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 6.4309. Min Range: -6.4309

Max Act: 4.9530. Min Act: -0.0000

Data Index: 429505 (C4 (Web Text))

Max Activating Token Index: 288