Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1651 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0000

Data Index: 887435 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1095581 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1089068 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0679. Min Act: -0.0000

Data Index: 46015 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0591. Min Act: -0.0000

Data Index: 553012 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0550. Min Act: -0.0000

Data Index: 561191 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0532. Min Act: -0.0000

Data Index: 1298252 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0529. Min Act: -0.0000

Data Index: 113326 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0519. Min Act: -0.0000

Data Index: 852544 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1210315 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0515. Min Act: -0.0000

Data Index: 660971 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1027059 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1574908 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1399880 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0487. Min Act: -0.0000

Data Index: 977649 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1297678 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0506. Min Act: -0.0000

Data Index: 284880 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0472. Min Act: -0.0000

Data Index: 326358 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0447. Min Act: -0.0000

Data Index: 560653 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0466. Min Act: -0.0000

Data Index: 167738 (C4 (Web Text))

Max Activating Token Index: 50