Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4558 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0683. Min Range: -4.0683

Max Act: 4.0683. Min Act: -0.0000

Data Index: 1449966 (Python Code)

Max Activating Token Index: 791

Text #1

Max Range: 4.0683. Min Range: -4.0683

Max Act: 4.0670. Min Act: -0.0000

Data Index: 1412721 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 4.0683. Min Range: -4.0683

Max Act: 3.7966. Min Act: -0.0000

Data Index: 1615244 (Python Code)

Max Activating Token Index: 105

Text #3

Max Range: 4.0683. Min Range: -4.0683

Max Act: 3.4559. Min Act: -0.0000

Data Index: 278088 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 4.0683. Min Range: -4.0683

Max Act: 3.1616. Min Act: -0.0000

Data Index: 734353 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.9357. Min Act: -0.0000

Data Index: 1529733 (Python Code)

Max Activating Token Index: 687

Text #6

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.9283. Min Act: -0.0000

Data Index: 1358510 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 4.0683. Min Range: -4.0683

Max Act: 3.0253. Min Act: -0.0000

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.9469. Min Act: -0.0000

Data Index: 1577152 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.8482. Min Act: -0.0000

Data Index: 489629 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.7921. Min Act: -0.0000

Data Index: 1487410 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.6013. Min Act: -0.0000

Data Index: 523713 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.6043. Min Act: -0.0000

Data Index: 1623558 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.4836. Min Act: -0.0000

Data Index: 1439366 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.3357. Min Act: -0.0000

Data Index: 1174754 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.4429. Min Act: -0.0000

Data Index: 1466684 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.4515. Min Act: -0.0000

Data Index: 1453550 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.3117. Min Act: -0.0000

Data Index: 1371299 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.1551. Min Act: -0.0000

Data Index: 1444322 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 4.0683. Min Range: -4.0683

Max Act: 2.5198. Min Act: -0.0000

Data Index: 668971 (C4 (Web Text))

Max Activating Token Index: 944