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

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

Neuron 3443 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.8218. Min Act: -0.0000

Data Index: 586578 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7551. Min Act: -0.0000

Data Index: 237808 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7166. Min Act: -0.0000

Data Index: 160608 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1250864 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6731. Min Act: -0.0000

Data Index: 264743 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6483. Min Act: -0.0000

Data Index: 285977 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1558 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5585. Min Act: -0.0000

Data Index: 576763 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1336409 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5671. Min Act: -0.0000

Data Index: 568196 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1171633 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5606. Min Act: -0.0000

Data Index: 475326 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5226. Min Act: -0.0000

Data Index: 772135 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.4984. Min Act: -0.0000

Data Index: 699663 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5309. Min Act: -0.0000

Data Index: 842386 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1276863 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5248. Min Act: -0.0000

Data Index: 876365 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.4948. Min Act: -0.0000

Data Index: 90 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.5010. Min Act: -0.0000

Data Index: 609427 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.4990. Min Act: -0.0000

Data Index: 149249 (C4 (Web Text))

Max Activating Token Index: 168