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

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

Neuron 2755 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1532223 (Python Code)

Max Activating Token Index: 791

Text #1

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1042453 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1654747 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3504. Min Act: -0.0000

Data Index: 266841 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3640. Min Act: -0.0000

Data Index: 417169 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1398068 (Python Code)

Max Activating Token Index: 242

Text #6

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3523. Min Act: -0.0000

Data Index: 820147 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3571. Min Act: -0.0000

Data Index: 587712 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1385621 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1502516 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1460905 (Python Code)

Max Activating Token Index: 280

Text #11

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1402810 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1446514 (Python Code)

Max Activating Token Index: 202

Text #13

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3140. Min Act: -0.0000

Data Index: 254617 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1362745 (Python Code)

Max Activating Token Index: 891

Text #15

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1639522 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1412453 (Python Code)

Max Activating Token Index: 453

Text #17

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1367154 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2784. Min Act: -0.0000

Data Index: 21672 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1347801 (C4 (Web Text))

Max Activating Token Index: 739