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

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

Neuron 1373 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2789. Min Act: -0.0005

Data Index: 833867 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2667. Min Act: -0.0005

Data Index: 777452 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2816. Min Act: -0.0005

Data Index: 195597 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2735. Min Act: -0.0005

Data Index: 1151346 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2820. Min Act: -0.0005

Data Index: 1207932 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2703. Min Act: -0.0005

Data Index: 1259422 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2579. Min Act: -0.0005

Data Index: 788638 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2611. Min Act: -0.0005

Data Index: 1333307 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2694. Min Act: -0.0005

Data Index: 138448 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2506. Min Act: -0.0005

Data Index: 1246892 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2611. Min Act: -0.0005

Data Index: 7294 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2485. Min Act: -0.0005

Data Index: 1252526 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2581. Min Act: -0.0005

Data Index: 118713 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2572. Min Act: -0.0005

Data Index: 78591 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2529. Min Act: -0.0005

Data Index: 166043 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2536. Min Act: -0.0005

Data Index: 852894 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2540. Min Act: -0.0005

Data Index: 311350 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2522. Min Act: -0.0005

Data Index: 1041937 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2585. Min Act: -0.0005

Data Index: 1033540 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2486. Min Act: -0.0005

Data Index: 786291 (C4 (Web Text))

Max Activating Token Index: 879