Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 172 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0507. Min Act: -0.0005

Data Index: 1166944 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0495. Min Act: -0.0005

Data Index: 246662 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0005

Data Index: 1168567 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0450. Min Act: -0.0005

Data Index: 1231528 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0457. Min Act: -0.0005

Data Index: 882816 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0392. Min Act: -0.0005

Data Index: 106360 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0366. Min Act: -0.0005

Data Index: 1443329 (Python Code)

Max Activating Token Index: 550

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0367. Min Act: -0.0005

Data Index: 810049 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0411. Min Act: -0.0005

Data Index: 119211 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0407. Min Act: -0.0005

Data Index: 1330691 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0383. Min Act: -0.0005

Data Index: 567524 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0369. Min Act: -0.0005

Data Index: 1596469 (Python Code)

Max Activating Token Index: 581

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0335. Min Act: -0.0005

Data Index: 1607072 (Python Code)

Max Activating Token Index: 612

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0387. Min Act: -0.0005

Data Index: 1061056 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1646297 (Python Code)

Max Activating Token Index: 625

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0355. Min Act: -0.0005

Data Index: 559307 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0361. Min Act: -0.0005

Data Index: 240365 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0355. Min Act: -0.0005

Data Index: 1418068 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0335. Min Act: -0.0005

Data Index: 1626205 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0361. Min Act: -0.0005

Data Index: 1442003 (Python Code)

Max Activating Token Index: 734