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

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

Neuron 5011 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: 0.9663. Min Range: -0.9663

Max Act: 0.9663. Min Act: -0.0002

Data Index: 268513 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.9186. Min Act: -0.0002

Data Index: 455067 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.8789. Min Act: -0.0002

Data Index: 504872 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.8408. Min Act: -0.0002

Data Index: 128561 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.8006. Min Act: -0.0003

Data Index: 411045 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7713. Min Act: -0.0002

Data Index: 1165928 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7903. Min Act: -0.0002

Data Index: 376250 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.8140. Min Act: -0.0002

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7777. Min Act: -0.0002

Data Index: 64687 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7348. Min Act: -0.0002

Data Index: 68338 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7546. Min Act: -0.0002

Data Index: 301832 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7453. Min Act: -0.0003

Data Index: 564814 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7581. Min Act: -0.0002

Data Index: 1329481 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7374. Min Act: -0.0002

Data Index: 851367 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7382. Min Act: -0.0002

Data Index: 306769 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7199. Min Act: -0.0002

Data Index: 336450 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7327. Min Act: -0.0002

Data Index: 1047423 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7501. Min Act: -0.0003

Data Index: 354073 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7315. Min Act: -0.0002

Data Index: 12612 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7306. Min Act: -0.0002

Data Index: 186859 (C4 (Web Text))

Max Activating Token Index: 772