Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2834 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0003

Data Index: 525510 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0646. Min Act: -0.0003

Data Index: 357052 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0588. Min Act: -0.0003

Data Index: 577672 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0588. Min Act: -0.0003

Data Index: 826506 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1038602 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0580. Min Act: -0.0003

Data Index: 929476 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1112620 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1142319 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0543. Min Act: -0.0003

Data Index: 19189 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1120745 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0536. Min Act: -0.0003

Data Index: 475651 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0547. Min Act: -0.0003

Data Index: 216467 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0494. Min Act: -0.0003

Data Index: 183526 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1341250 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0522. Min Act: -0.0003

Data Index: 787115 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0520. Min Act: -0.0003

Data Index: 833616 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0491. Min Act: -0.0003

Data Index: 207295 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1184548 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0489. Min Act: -0.0003

Data Index: 894176 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0545. Min Act: -0.0003

Data Index: 712603 (C4 (Web Text))

Max Activating Token Index: 505