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

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

Neuron 3628 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0002

Data Index: 145653 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1010671 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0298. Min Act: -0.0002

Data Index: 474388 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0298. Min Act: -0.0002

Data Index: 478006 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0298. Min Act: -0.0002

Data Index: 150468 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0298. Min Act: -0.0002

Data Index: 639449 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0295. Min Act: -0.0002

Data Index: 28881 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0288. Min Act: -0.0002

Data Index: 111021 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0291. Min Act: -0.0002

Data Index: 808084 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0291. Min Act: -0.0002

Data Index: 656647 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0288. Min Act: -0.0002

Data Index: 533085 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0286. Min Act: -0.0002

Data Index: 142929 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0285. Min Act: -0.0002

Data Index: 152038 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0285. Min Act: -0.0002

Data Index: 56145 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0285. Min Act: -0.0002

Data Index: 569581 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0285. Min Act: -0.0002

Data Index: 270607 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0285. Min Act: -0.0002

Data Index: 460324 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0285. Min Act: -0.0002

Data Index: 404614 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0285. Min Act: -0.0002

Data Index: 32453 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0285. Min Act: -0.0002

Data Index: 532631 (C4 (Web Text))

Max Activating Token Index: 1