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

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

Neuron 4124 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.7534. Min Act: -0.0000

Data Index: 224363 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1109444 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1215404 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5556. Min Act: -0.0000

Data Index: 180865 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1217141 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6671. Min Act: -0.0000

Data Index: 214982 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6123. Min Act: -0.0000

Data Index: 517707 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1354296 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.6235. Min Act: -0.0000

Data Index: 377916 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1039544 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5056. Min Act: -0.0000

Data Index: 414369 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5789. Min Act: -0.0000

Data Index: 512826 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5355. Min Act: -0.0000

Data Index: 471825 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5212. Min Act: -0.0000

Data Index: 374560 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1599535 (Python Code)

Max Activating Token Index: 165

Text #15

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5215. Min Act: -0.0000

Data Index: 252404 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5338. Min Act: -0.0000

Data Index: 955610 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5246. Min Act: -0.0000

Data Index: 260626 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5520. Min Act: -0.0000

Data Index: 777954 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.7534. Min Range: -0.7534

Max Act: 0.5550. Min Act: -0.0000

Data Index: 178798 (C4 (Web Text))

Max Activating Token Index: 222