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

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

Neuron 4697 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1582106 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1646609 (Python Code)

Max Activating Token Index: 769

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1542399 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1655792 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0445. Min Act: -0.0002

Data Index: 748465 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1617933 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1507064 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1198839 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1621773 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1558917 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1582747 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1370053 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0420. Min Act: -0.0002

Data Index: 490499 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1643229 (Python Code)

Max Activating Token Index: 281

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1301527 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1554786 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1435471 (Python Code)

Max Activating Token Index: 681

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1492051 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0412. Min Act: -0.0002

Data Index: 862590 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1646143 (Python Code)

Max Activating Token Index: 67