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

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

Neuron 2373 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0309. Min Range: -1.0309

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1429603 (Python Code)

Max Activating Token Index: 253

Text #1

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7475. Min Act: 0.0000

Data Index: 399554 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1653149 (Python Code)

Max Activating Token Index: 123

Text #3

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1440990 (Python Code)

Max Activating Token Index: 978

Text #4

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1388161 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1596723 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1628334 (Python Code)

Max Activating Token Index: 242

Text #7

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1456308 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1451446 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1569107 (Python Code)

Max Activating Token Index: 538

Text #10

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1631199 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.5975. Min Act: 0.0000

Data Index: 1433889 (Python Code)

Max Activating Token Index: 457

Text #12

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1646100 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1588776 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1452174 (Python Code)

Max Activating Token Index: 101

Text #15

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.6485. Min Act: 0.0000

Data Index: 1420612 (Python Code)

Max Activating Token Index: 808

Text #16

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1631998 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1572074 (Python Code)

Max Activating Token Index: 821

Text #18

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1401224 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 1.0309. Min Range: -1.0309

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1325686 (C4 (Web Text))

Max Activating Token Index: 71