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

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

Neuron 2712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2734. Min Act: -0.0000

Data Index: 1433812 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1127. Min Act: -0.0000

Data Index: 1427032 (Python Code)

Max Activating Token Index: 430

Text #2

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2340. Min Act: -0.0000

Data Index: 1513081 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.0396. Min Act: -0.0000

Data Index: 1552549 (Python Code)

Max Activating Token Index: 138

Text #4

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.9659. Min Act: -0.0000

Data Index: 1557672 (Python Code)

Max Activating Token Index: 944

Text #5

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.0895. Min Act: -0.0000

Data Index: 1490540 (Python Code)

Max Activating Token Index: 671

Text #6

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.9468. Min Act: -0.0000

Data Index: 1418303 (Python Code)

Max Activating Token Index: 429

Text #7

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.8426. Min Act: -0.0000

Data Index: 1365713 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.7496. Min Act: -0.0000

Data Index: 1581212 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.6970. Min Act: -0.0000

Data Index: 1373751 (Python Code)

Max Activating Token Index: 588

Text #10

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.6810. Min Act: -0.0000

Data Index: 1386036 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.6382. Min Act: -0.0000

Data Index: 1526144 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.4911. Min Act: -0.0000

Data Index: 1549827 (Python Code)

Max Activating Token Index: 120

Text #13

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.5980. Min Act: -0.0000

Data Index: 1599870 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.4221. Min Act: -0.0000

Data Index: 1390997 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.5370. Min Act: -0.0000

Data Index: 1650171 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.5232. Min Act: -0.0000

Data Index: 1464453 (Python Code)

Max Activating Token Index: 664

Text #17

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.2796. Min Act: -0.0000

Data Index: 1540828 (Python Code)

Max Activating Token Index: 147

Text #18

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.3583. Min Act: -0.0000

Data Index: 1413066 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.3196. Min Act: -0.0000

Data Index: 1533368 (Python Code)

Max Activating Token Index: 217