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

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

Neuron 259 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3637. Min Range: -5.3637

Max Act: 5.3637. Min Act: -0.0000

Data Index: 1511439 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.8390. Min Act: -0.0000

Data Index: 1376653 (Python Code)

Max Activating Token Index: 423

Text #2

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.4287. Min Act: -0.0000

Data Index: 1611495 (Python Code)

Max Activating Token Index: 837

Text #3

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.0333. Min Act: -0.0000

Data Index: 1516644 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.8221. Min Act: -0.0000

Data Index: 1361520 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.9971. Min Act: -0.0000

Data Index: 1471477 (Python Code)

Max Activating Token Index: 375

Text #6

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.1558. Min Act: -0.0000

Data Index: 1589923 (Python Code)

Max Activating Token Index: 928

Text #7

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.1620. Min Act: -0.0000

Data Index: 1430408 (Python Code)

Max Activating Token Index: 255

Text #8

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.6944. Min Act: -0.0000

Data Index: 1648773 (Python Code)

Max Activating Token Index: 558

Text #9

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.2221. Min Act: -0.0000

Data Index: 1652764 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.9850. Min Act: -0.0000

Data Index: 1569503 (Python Code)

Max Activating Token Index: 839

Text #11

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.7298. Min Act: -0.0000

Data Index: 1585467 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.9513. Min Act: -0.0000

Data Index: 1556198 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.7045. Min Act: -0.0000

Data Index: 1401741 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.8103. Min Act: -0.0000

Data Index: 1446241 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.9658. Min Act: -0.0000

Data Index: 1649553 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.6171. Min Act: -0.0000

Data Index: 1437666 (Python Code)

Max Activating Token Index: 772

Text #17

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.6427. Min Act: -0.0000

Data Index: 955641 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 5.3637. Min Range: -5.3637

Max Act: 3.6324. Min Act: -0.0000

Data Index: 1510677 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 5.3637. Min Range: -5.3637

Max Act: 4.1197. Min Act: -0.0000

Data Index: 1184190 (C4 (Web Text))

Max Activating Token Index: 236