Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 682 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0021. Min Range: -1.0021

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1270041 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8663. Min Act: -0.0000

Data Index: 360467 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7284. Min Act: -0.0000

Data Index: 297377 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6528. Min Act: -0.0000

Data Index: 457518 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1297531 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6814. Min Act: -0.0000

Data Index: 181356 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6967. Min Act: -0.0000

Data Index: 875361 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1030156 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7203. Min Act: -0.0000

Data Index: 183488 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1204325 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6882. Min Act: -0.0000

Data Index: 284757 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1200753 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6772. Min Act: -0.0001

Data Index: 16394 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6742. Min Act: -0.0000

Data Index: 642377 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7171. Min Act: -0.0000

Data Index: 147216 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6585. Min Act: -0.0000

Data Index: 417795 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6947. Min Act: -0.0000

Data Index: 176670 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6557. Min Act: -0.0000

Data Index: 459510 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6819. Min Act: -0.0000

Data Index: 6143 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1336275 (C4 (Web Text))

Max Activating Token Index: 213