Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5030 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1436377 (Python Code)

Max Activating Token Index: 466

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1044181 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0542. Min Act: -0.0002

Data Index: 789723 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0542. Min Act: -0.0002

Data Index: 138662 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1000791 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0529. Min Act: -0.0002

Data Index: 816907 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0003

Data Index: 526224 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1466933 (Python Code)

Max Activating Token Index: 282

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0506. Min Act: -0.0002

Data Index: 352812 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0515. Min Act: -0.0002

Data Index: 397138 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1140897 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1473057 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0517. Min Act: -0.0002

Data Index: 975948 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1513843 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0504. Min Act: -0.0003

Data Index: 589437 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0515. Min Act: -0.0002

Data Index: 667352 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0506. Min Act: -0.0002

Data Index: 2692 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0500. Min Act: -0.0002

Data Index: 682731 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1502181 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0482. Min Act: -0.0003

Data Index: 638661 (C4 (Web Text))

Max Activating Token Index: 1006