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

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

Neuron 4120 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9232. Min Act: -0.0002

Data Index: 1651686 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8817. Min Act: -0.0002

Data Index: 1645675 (Python Code)

Max Activating Token Index: 246

Text #2

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6812. Min Act: -0.0002

Data Index: 1532672 (Python Code)

Max Activating Token Index: 464

Text #3

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9427. Min Act: -0.0002

Data Index: 1494147 (Python Code)

Max Activating Token Index: 566

Text #4

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9392. Min Act: -0.0002

Data Index: 1566631 (Python Code)

Max Activating Token Index: 157

Text #5

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9600. Min Act: -0.0002

Data Index: 1515373 (Python Code)

Max Activating Token Index: 789

Text #6

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8529. Min Act: -0.0002

Data Index: 1406451 (Python Code)

Max Activating Token Index: 236

Text #7

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8916. Min Act: -0.0002

Data Index: 1379993 (Python Code)

Max Activating Token Index: 712

Text #8

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7834. Min Act: -0.0002

Data Index: 1423895 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8291. Min Act: -0.0002

Data Index: 1360945 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7765. Min Act: -0.0002

Data Index: 1450064 (Python Code)

Max Activating Token Index: 813

Text #11

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7506. Min Act: -0.0002

Data Index: 1483843 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7279. Min Act: -0.0002

Data Index: 1623724 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7854. Min Act: -0.0002

Data Index: 1609792 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9086. Min Act: -0.0002

Data Index: 1438211 (Python Code)

Max Activating Token Index: 602

Text #15

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6965. Min Act: -0.0002

Data Index: 1569248 (Python Code)

Max Activating Token Index: 372

Text #16

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8063. Min Act: -0.0002

Data Index: 1391632 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7531. Min Act: -0.0002

Data Index: 1539133 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8192. Min Act: -0.0002

Data Index: 1452343 (Python Code)

Max Activating Token Index: 446

Text #19

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8871. Min Act: -0.0002

Data Index: 1642578 (Python Code)

Max Activating Token Index: 464