Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 621 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0002

Data Index: 677395 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0573. Min Act: -0.0002

Data Index: 294375 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0002

Data Index: 124208 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1086920 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1017169 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0577. Min Act: -0.0001

Data Index: 634019 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0556. Min Act: -0.0002

Data Index: 349278 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1033486 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0539. Min Act: -0.0002

Data Index: 444930 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1676 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0532. Min Act: -0.0002

Data Index: 950326 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0536. Min Act: -0.0002

Data Index: 901660 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0526. Min Act: -0.0002

Data Index: 630668 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0509. Min Act: -0.0002

Data Index: 150507 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0526. Min Act: -0.0002

Data Index: 312767 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0527. Min Act: -0.0002

Data Index: 362832 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0489. Min Act: -0.0002

Data Index: 40534 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0505. Min Act: -0.0002

Data Index: 132148 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0512. Min Act: -0.0002

Data Index: 779934 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0499. Min Act: -0.0002

Data Index: 345657 (C4 (Web Text))

Max Activating Token Index: 757