Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 891 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1349390 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0001

Data Index: 709556 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0743. Min Act: -0.0001

Data Index: 998210 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0717. Min Act: -0.0001

Data Index: 970827 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0683. Min Act: -0.0001

Data Index: 260494 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0700. Min Act: -0.0001

Data Index: 501015 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1143523 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0618. Min Act: -0.0001

Data Index: 55725 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0625. Min Act: -0.0001

Data Index: 480112 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1294182 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1462366 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1089159 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1604891 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0622. Min Act: -0.0001

Data Index: 994634 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1559161 (Python Code)

Max Activating Token Index: 175

Text #15

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1425409 (Python Code)

Max Activating Token Index: 364

Text #16

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1457091 (Python Code)

Max Activating Token Index: 739

Text #17

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1048086 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0589. Min Act: -0.0001

Data Index: 643293 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0602. Min Act: -0.0001

Data Index: 879690 (C4 (Web Text))

Max Activating Token Index: 295