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

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

Neuron 2719 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: 0.0763. Min Range: -0.0763

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1515001 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1483096 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0683. Min Act: -0.0002

Data Index: 600515 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 581313 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0653. Min Act: -0.0002

Data Index: 365021 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1038008 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1538008 (Python Code)

Max Activating Token Index: 296

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0537. Min Act: -0.0002

Data Index: 635304 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1589939 (Python Code)

Max Activating Token Index: 218

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1161669 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1414412 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1573293 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1532945 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1513343 (Python Code)

Max Activating Token Index: 754

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0581. Min Act: -0.0002

Data Index: 500387 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1499693 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0502. Min Act: -0.0002

Data Index: 659048 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1380270 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1336110 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0515. Min Act: -0.0002

Data Index: 716781 (C4 (Web Text))

Max Activating Token Index: 663