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

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

Neuron 1374 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.6023. Min Act: -0.0000

Data Index: 259058 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.5672. Min Act: 0.0000

Data Index: 1082791 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.5243. Min Act: 0.0000

Data Index: 992391 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4928. Min Act: -0.0000

Data Index: 969921 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.5106. Min Act: -0.0000

Data Index: 390303 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4921. Min Act: 0.0000

Data Index: 910162 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4721. Min Act: -0.0000

Data Index: 369831 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4529. Min Act: -0.0000

Data Index: 781906 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4702. Min Act: -0.0000

Data Index: 664004 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4627. Min Act: -0.0000

Data Index: 808072 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4669. Min Act: 0.0000

Data Index: 287101 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4607. Min Act: -0.0000

Data Index: 803461 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4468. Min Act: 0.0000

Data Index: 500752 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4394. Min Act: -0.0000

Data Index: 502514 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4148. Min Act: -0.0000

Data Index: 152135 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1072039 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4368. Min Act: -0.0000

Data Index: 816576 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4329. Min Act: -0.0000

Data Index: 832444 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4170. Min Act: -0.0000

Data Index: 67057 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.6023. Min Range: -0.6023

Max Act: 0.4229. Min Act: 0.0001

Data Index: 1183064 (C4 (Web Text))

Max Activating Token Index: 72