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

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

Neuron 4520 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5483. Min Act: -0.0000

Data Index: 398539 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5736. Min Act: -0.0000

Data Index: 1348889 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4438. Min Act: -0.0000

Data Index: 75632 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.3958. Min Act: -0.0000

Data Index: 1238629 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4241. Min Act: -0.0000

Data Index: 886694 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.3699. Min Act: -0.0000

Data Index: 616290 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4329. Min Act: -0.0000

Data Index: 411439 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.3031. Min Act: -0.0000

Data Index: 499585 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4580. Min Act: -0.0000

Data Index: 218052 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.3562. Min Act: -0.0000

Data Index: 1152513 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4631. Min Act: -0.0000

Data Index: 349851 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1307155 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.4394. Min Act: -0.0000

Data Index: 410730 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1218082 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1063605 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2908. Min Act: -0.0000

Data Index: 587546 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.3205. Min Act: -0.0000

Data Index: 334021 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1196177 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2448. Min Act: -0.0000

Data Index: 767376 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.2734. Min Act: -0.0000

Data Index: 978418 (C4 (Web Text))

Max Activating Token Index: 645