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

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

Neuron 101 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.4101. Min Act: -0.0000

Data Index: 1381409 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.4753. Min Act: -0.0000

Data Index: 1391650 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.4224. Min Act: -0.0000

Data Index: 1615583 (Python Code)

Max Activating Token Index: 497

Text #3

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.3895. Min Act: -0.0000

Data Index: 1518942 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.2382. Min Act: -0.0000

Data Index: 1455003 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.2659. Min Act: -0.0000

Data Index: 1374686 (Python Code)

Max Activating Token Index: 816

Text #6

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.1061. Min Act: -0.0000

Data Index: 1428260 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.9874. Min Act: -0.0000

Data Index: 1637353 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.0761. Min Act: -0.0000

Data Index: 1547223 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.9470. Min Act: -0.0000

Data Index: 1514236 (Python Code)

Max Activating Token Index: 369

Text #10

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.1491. Min Act: -0.0000

Data Index: 1650420 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.9425. Min Act: -0.0000

Data Index: 1482960 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.1080. Min Act: -0.0000

Data Index: 1529526 (Python Code)

Max Activating Token Index: 464

Text #13

Max Range: 2.4753. Min Range: -2.4753

Max Act: 2.1092. Min Act: -0.0000

Data Index: 1433130 (Python Code)

Max Activating Token Index: 241

Text #14

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.9369. Min Act: -0.0000

Data Index: 1620920 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.9397. Min Act: -0.0000

Data Index: 1378258 (Python Code)

Max Activating Token Index: 581

Text #16

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.9065. Min Act: -0.0000

Data Index: 1419332 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1556895 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1452414 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 2.4753. Min Range: -2.4753

Max Act: 1.8894. Min Act: -0.0000

Data Index: 1600545 (Python Code)

Max Activating Token Index: 429