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

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

Neuron 4792 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1582990 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0522. Min Act: -0.0002

Data Index: 759918 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0553. Min Act: -0.0002

Data Index: 509941 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1589719 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1389806 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0530. Min Act: -0.0002

Data Index: 423227 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0546. Min Act: -0.0002

Data Index: 365025 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0492. Min Act: -0.0002

Data Index: 997424 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0490. Min Act: -0.0002

Data Index: 513555 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0517. Min Act: -0.0002

Data Index: 843634 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0499. Min Act: -0.0002

Data Index: 521822 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0503. Min Act: -0.0002

Data Index: 330167 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1220859 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0476. Min Act: -0.0002

Data Index: 478184 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0479. Min Act: -0.0002

Data Index: 714271 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0453. Min Act: -0.0002

Data Index: 510895 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0467. Min Act: -0.0002

Data Index: 13435 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0450. Min Act: -0.0002

Data Index: 898953 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1341008 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1599543 (Python Code)

Max Activating Token Index: 820