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

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

Neuron 750 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: 1.9556. Min Range: -1.9556

Max Act: 1.9556. Min Act: -0.0000

Data Index: 612259 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.3897. Min Act: -0.0000

Data Index: 1050879 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.2492. Min Act: -0.0000

Data Index: 715838 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.0948. Min Act: -0.0000

Data Index: 789971 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.0804. Min Act: -0.0000

Data Index: 708758 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.0215. Min Act: -0.0000

Data Index: 512413 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.9729. Min Act: -0.0000

Data Index: 182281 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.9245. Min Act: -0.0000

Data Index: 230425 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.8763. Min Act: -0.0000

Data Index: 358628 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1517160 (Python Code)

Max Activating Token Index: 808

Text #10

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.8477. Min Act: -0.0000

Data Index: 806406 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.8005. Min Act: -0.0000

Data Index: 828221 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1508803 (Python Code)

Max Activating Token Index: 610

Text #13

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1592467 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1331362 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.8200. Min Act: -0.0000

Data Index: 525064 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.8245. Min Act: -0.0000

Data Index: 269266 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1213379 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1522987 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 1.9556. Min Range: -1.9556

Max Act: 0.7590. Min Act: -0.0000

Data Index: 96496 (C4 (Web Text))

Max Activating Token Index: 985