Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 70 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1590343 (Python Code)

Max Activating Token Index: 208

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1581885 (Python Code)

Max Activating Token Index: 678

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1504679 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1597504 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1378939 (Python Code)

Max Activating Token Index: 623

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0453. Min Act: -0.0002

Data Index: 155335 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1414031 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1583004 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1635440 (Python Code)

Max Activating Token Index: 731

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0423. Min Act: -0.0002

Data Index: 166442 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1451653 (Python Code)

Max Activating Token Index: 258

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1222758 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1589584 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0406. Min Act: -0.0002

Data Index: 646112 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1571039 (Python Code)

Max Activating Token Index: 111

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0410. Min Act: -0.0002

Data Index: 496468 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0408. Min Act: -0.0002

Data Index: 129456 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1625734 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1532177 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1401762 (Python Code)

Max Activating Token Index: 250