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

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

Neuron 3409 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.5998. Min Act: -0.0000

Data Index: 93097 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1238456 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.5022. Min Act: -0.0000

Data Index: 773643 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4833. Min Act: -0.0000

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4997. Min Act: -0.0000

Data Index: 138690 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.5484. Min Act: -0.0000

Data Index: 782889 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.5104. Min Act: -0.0000

Data Index: 425205 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.5042. Min Act: -0.0000

Data Index: 94927 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4650. Min Act: -0.0000

Data Index: 416606 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1295160 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4563. Min Act: -0.0000

Data Index: 928899 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4486. Min Act: -0.0000

Data Index: 454000 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4811. Min Act: -0.0000

Data Index: 891300 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1004336 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4262. Min Act: -0.0000

Data Index: 115109 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.3784. Min Act: -0.0000

Data Index: 121732 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4526. Min Act: -0.0000

Data Index: 210199 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1024157 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4183. Min Act: -0.0000

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.5998. Min Range: -0.5998

Max Act: 0.4300. Min Act: -0.0000

Data Index: 257558 (C4 (Web Text))

Max Activating Token Index: 24