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

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

Neuron 1595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.9318. Min Act: -0.0000

Data Index: 368564 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1514912 (Python Code)

Max Activating Token Index: 397

Text #2

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6456. Min Act: -0.0000

Data Index: 862822 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1126590 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1226869 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1574865 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1559581 (Python Code)

Max Activating Token Index: 876

Text #7

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5449. Min Act: -0.0000

Data Index: 405385 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1365002 (Python Code)

Max Activating Token Index: 894

Text #9

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1426715 (Python Code)

Max Activating Token Index: 233

Text #10

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5431. Min Act: -0.0000

Data Index: 305361 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5132. Min Act: -0.0000

Data Index: 492755 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5472. Min Act: -0.0000

Data Index: 737436 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5549. Min Act: -0.0000

Data Index: 807364 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1557324 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5113. Min Act: -0.0000

Data Index: 538767 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1475558 (Python Code)

Max Activating Token Index: 128

Text #17

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1445014 (Python Code)

Max Activating Token Index: 362

Text #18

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5232. Min Act: -0.0000

Data Index: 553076 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1568373 (Python Code)

Max Activating Token Index: 527