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

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

Neuron 1171 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1534. Min Range: -4.1534

Max Act: 4.1534. Min Act: -0.0000

Data Index: 232851 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 4.1534. Min Range: -4.1534

Max Act: 4.1457. Min Act: -0.0000

Data Index: 302794 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.9134. Min Act: -0.0000

Data Index: 552372 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.9676. Min Act: -0.0000

Data Index: 99738 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.7251. Min Act: -0.0000

Data Index: 1222400 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.5151. Min Act: -0.0000

Data Index: 827757 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.4858. Min Act: -0.0000

Data Index: 86334 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.4358. Min Act: -0.0000

Data Index: 699267 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.4098. Min Act: -0.0000

Data Index: 138424 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.3763. Min Act: -0.0000

Data Index: 706796 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.4451. Min Act: -0.0000

Data Index: 68851 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.2741. Min Act: -0.0000

Data Index: 174890 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 4.1534. Min Range: -4.1534

Max Act: 2.1279. Min Act: -0.0000

Data Index: 1153919 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 4.1534. Min Range: -4.1534

Max Act: 2.2357. Min Act: -0.0000

Data Index: 472085 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 4.1534. Min Range: -4.1534

Max Act: 2.3140. Min Act: -0.0000

Data Index: 283167 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 4.1534. Min Range: -4.1534

Max Act: 2.1373. Min Act: -0.0000

Data Index: 17765 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 4.1534. Min Range: -4.1534

Max Act: 2.2590. Min Act: -0.0000

Data Index: 381858 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 4.1534. Min Range: -4.1534

Max Act: 1.9246. Min Act: -0.0000

Data Index: 428718 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 4.1534. Min Range: -4.1534

Max Act: 1.8420. Min Act: -0.0000

Data Index: 1045493 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 4.1534. Min Range: -4.1534

Max Act: 1.7317. Min Act: -0.0000

Data Index: 829232 (C4 (Web Text))

Max Activating Token Index: 596