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

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

Neuron 3836 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.7805. Min Act: -0.0000

Data Index: 1535298 (Python Code)

Max Activating Token Index: 1010

Text #1

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.8561. Min Act: -0.0000

Data Index: 1600123 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.8346. Min Act: -0.0000

Data Index: 1587475 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.8193. Min Act: 0.0001

Data Index: 1643679 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.7105. Min Act: 0.0000

Data Index: 1630314 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.7632. Min Act: -0.0000

Data Index: 1480116 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1547687 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.7285. Min Act: -0.0000

Data Index: 1394580 (Python Code)

Max Activating Token Index: 470

Text #8

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.6615. Min Act: 0.0000

Data Index: 1415286 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1507231 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.5795. Min Act: -0.0000

Data Index: 1389815 (Python Code)

Max Activating Token Index: 637

Text #11

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1611441 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.5349. Min Act: -0.0000

Data Index: 1443009 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.6280. Min Act: -0.0000

Data Index: 1492504 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.5329. Min Act: -0.0000

Data Index: 1421863 (Python Code)

Max Activating Token Index: 202

Text #15

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.6131. Min Act: -0.0000

Data Index: 1526695 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.5736. Min Act: -0.0000

Data Index: 1558289 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.4746. Min Act: -0.0000

Data Index: 1651054 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.5613. Min Act: -0.0000

Data Index: 1385125 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 1.8561. Min Range: -1.8561

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1574821 (Python Code)

Max Activating Token Index: 73