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

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

Neuron 3743 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.2815. Min Act: -0.0000

Data Index: 1284926 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1247719 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1420. Min Act: -0.0000

Data Index: 799366 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1115752 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0339. Min Act: -0.0000

Data Index: 356444 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0307. Min Act: -0.0000

Data Index: 615304 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.9031. Min Act: -0.0000

Data Index: 845568 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1136517 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.8934. Min Act: -0.0000

Data Index: 58639 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.8708. Min Act: -0.0000

Data Index: 427502 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.8590. Min Act: -0.0000

Data Index: 995223 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.8239. Min Act: -0.0000

Data Index: 396812 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1308825 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1219820 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1302821 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.7532. Min Act: -0.0000

Data Index: 372537 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1165853 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.7923. Min Act: -0.0000

Data Index: 345621 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1636832 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.7543. Min Act: -0.0000

Data Index: 318095 (C4 (Web Text))

Max Activating Token Index: 628