Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 820 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0656. Min Act: -0.0002

Data Index: 644138 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1328425 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0567. Min Act: -0.0003

Data Index: 99701 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1217019 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0548. Min Act: -0.0002

Data Index: 567009 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0545. Min Act: -0.0003

Data Index: 449833 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0529. Min Act: -0.0003

Data Index: 752649 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0523. Min Act: -0.0002

Data Index: 186800 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0497. Min Act: -0.0002

Data Index: 81721 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0512. Min Act: -0.0002

Data Index: 528084 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1127995 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1215784 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1146900 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1276854 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0507. Min Act: -0.0003

Data Index: 402993 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0500. Min Act: -0.0003

Data Index: 114005 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0499. Min Act: -0.0003

Data Index: 362655 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1187477 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0495. Min Act: -0.0002

Data Index: 650220 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1131965 (C4 (Web Text))

Max Activating Token Index: 350