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

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

Neuron 3833 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.8211. Min Act: -0.0000

Data Index: 473003 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.5953. Min Act: -0.0000

Data Index: 748107 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.5452. Min Act: -0.0000

Data Index: 1409018 (Python Code)

Max Activating Token Index: 440

Text #3

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.4602. Min Act: -0.0000

Data Index: 648776 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.4612. Min Act: -0.0000

Data Index: 281547 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.4060. Min Act: -0.0000

Data Index: 1136132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.2841. Min Act: -0.0000

Data Index: 307617 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.3668. Min Act: -0.0000

Data Index: 1323205 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.3752. Min Act: -0.0000

Data Index: 1287073 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.3456. Min Act: -0.0000

Data Index: 1331794 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.3578. Min Act: -0.0000

Data Index: 183154 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.4417. Min Act: -0.0000

Data Index: 698421 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.2870. Min Act: -0.0000

Data Index: 281606 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.2425. Min Act: -0.0000

Data Index: 54265 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.2444. Min Act: -0.0000

Data Index: 1232833 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.0924. Min Act: -0.0000

Data Index: 641327 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.0600. Min Act: -0.0000

Data Index: 831729 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.2882. Min Act: -0.0000

Data Index: 817653 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.1431. Min Act: -0.0000

Data Index: 984684 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 2.8211. Min Range: -2.8211

Max Act: 2.0474. Min Act: -0.0000

Data Index: 580168 (C4 (Web Text))

Max Activating Token Index: 15