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

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

Neuron 5090 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.6067. Min Act: -0.0001

Data Index: 110528 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.5237. Min Act: -0.0001

Data Index: 1268464 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.4276. Min Act: -0.0001

Data Index: 959793 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.3618. Min Act: -0.0001

Data Index: 124074 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.3751. Min Act: -0.0001

Data Index: 586883 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.3561. Min Act: -0.0001

Data Index: 1172724 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.3106. Min Act: -0.0001

Data Index: 863072 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.3157. Min Act: -0.0001

Data Index: 1228477 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.3006. Min Act: -0.0001

Data Index: 433790 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.2668. Min Act: -0.0001

Data Index: 713908 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.2581. Min Act: -0.0001

Data Index: 692762 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.1333. Min Act: -0.0001

Data Index: 658085 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.2463. Min Act: -0.0001

Data Index: 697675 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.1766. Min Act: -0.0001

Data Index: 961915 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.2281. Min Act: -0.0001

Data Index: 438007 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.1883. Min Act: -0.0001

Data Index: 753675 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.2374. Min Act: -0.0001

Data Index: 122504 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.2008. Min Act: -0.0001

Data Index: 88342 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.2538. Min Act: -0.0001

Data Index: 274252 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.1731. Min Act: -0.0001

Data Index: 526378 (C4 (Web Text))

Max Activating Token Index: 843