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

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

Neuron 4877 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.3900. Min Act: -0.0000

Data Index: 968959 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1474435 (Python Code)

Max Activating Token Index: 170

Text #2

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1629283 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1306167 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1397. Min Act: -0.0000

Data Index: 961414 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0971. Min Act: -0.0000

Data Index: 580460 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1680. Min Act: -0.0000

Data Index: 387456 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1466853 (Python Code)

Max Activating Token Index: 607

Text #8

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1641410 (Python Code)

Max Activating Token Index: 724

Text #9

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1445173 (Python Code)

Max Activating Token Index: 135

Text #10

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.1520. Min Act: -0.0000

Data Index: 748077 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1360891 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0395. Min Act: -0.0000

Data Index: 1492165 (Python Code)

Max Activating Token Index: 988

Text #13

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9728. Min Act: -0.0000

Data Index: 9488 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1457379 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9364. Min Act: 0.0000

Data Index: 1584698 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0214. Min Act: -0.0000

Data Index: 602001 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1455362 (Python Code)

Max Activating Token Index: 772

Text #18

Max Range: 1.3900. Min Range: -1.3900

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1284727 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.3900. Min Range: -1.3900

Max Act: 1.0104. Min Act: -0.0000

Data Index: 799757 (C4 (Web Text))

Max Activating Token Index: 414