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

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

Neuron 927 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0405. Min Act: -0.0002

Data Index: 539214 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0002

Data Index: 838164 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1085201 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0437. Min Act: -0.0002

Data Index: 933503 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0419. Min Act: -0.0002

Data Index: 96665 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0367. Min Act: -0.0002

Data Index: 107566 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0383. Min Act: -0.0002

Data Index: 366676 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1406896 (Python Code)

Max Activating Token Index: 950

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0360. Min Act: -0.0002

Data Index: 569848 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0373. Min Act: -0.0002

Data Index: 749763 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0402. Min Act: -0.0002

Data Index: 118465 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0394. Min Act: -0.0002

Data Index: 610909 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0390. Min Act: -0.0002

Data Index: 24069 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0391. Min Act: -0.0002

Data Index: 702276 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0389. Min Act: -0.0002

Data Index: 893096 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1063192 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0395. Min Act: -0.0002

Data Index: 950262 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0352. Min Act: -0.0002

Data Index: 927867 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0354. Min Act: -0.0002

Data Index: 203058 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1017151 (C4 (Web Text))

Max Activating Token Index: 254