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

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

Neuron 965 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: 2.1655. Min Range: -2.1655

Max Act: 2.1655. Min Act: -0.0000

Data Index: 563407 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 2.1655. Min Range: -2.1655

Max Act: 2.0963. Min Act: -0.0000

Data Index: 635042 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 2.1655. Min Range: -2.1655

Max Act: 2.0652. Min Act: -0.0000

Data Index: 839270 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 2.1655. Min Range: -2.1655

Max Act: 2.0555. Min Act: -0.0000

Data Index: 619508 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 2.1655. Min Range: -2.1655

Max Act: 2.0299. Min Act: -0.0000

Data Index: 597540 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 2.1655. Min Range: -2.1655

Max Act: 2.0186. Min Act: -0.0000

Data Index: 269870 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.9868. Min Act: -0.0000

Data Index: 657067 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.8941. Min Act: -0.0000

Data Index: 381751 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.9327. Min Act: -0.0000

Data Index: 367926 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.8420. Min Act: -0.0000

Data Index: 447759 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.8450. Min Act: -0.0000

Data Index: 1247775 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.9476. Min Act: -0.0000

Data Index: 468975 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.9787. Min Act: -0.0000

Data Index: 1295119 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.9274. Min Act: -0.0000

Data Index: 413310 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1059620 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.9356. Min Act: -0.0000

Data Index: 852517 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.8819. Min Act: -0.0000

Data Index: 323112 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.8692. Min Act: -0.0000

Data Index: 801744 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.8648. Min Act: -0.0000

Data Index: 1062922 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 2.1655. Min Range: -2.1655

Max Act: 1.8444. Min Act: -0.0000

Data Index: 648657 (C4 (Web Text))

Max Activating Token Index: 553