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

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

Neuron 4701 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0001

Data Index: 884634 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0510. Min Act: -0.0001

Data Index: 942116 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1193387 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0585. Min Act: -0.0001

Data Index: 649091 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0516. Min Act: -0.0001

Data Index: 1624276 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1555087 (Python Code)

Max Activating Token Index: 137

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0533. Min Act: -0.0001

Data Index: 897872 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0423. Min Act: -0.0001

Data Index: 447090 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1077948 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0403. Min Act: -0.0001

Data Index: 456015 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0443. Min Act: -0.0001

Data Index: 701625 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0458. Min Act: -0.0001

Data Index: 782032 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0434. Min Act: -0.0001

Data Index: 159801 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1171648 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1593476 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0485. Min Act: -0.0001

Data Index: 406795 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1557943 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0408. Min Act: -0.0001

Data Index: 24235 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0426. Min Act: -0.0001

Data Index: 911699 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1612836 (Python Code)

Max Activating Token Index: 824