Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2010 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2746. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1620820 (Python Code)

Max Activating Token Index: 60

Text #2

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1395554 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2518. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2419. Min Act: -0.0001

Data Index: 1522152 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2290. Min Act: -0.0001

Data Index: 1501597 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2194. Min Act: -0.0001

Data Index: 1609081 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2402. Min Act: -0.0001

Data Index: 1504989 (Python Code)

Max Activating Token Index: 700

Text #8

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2121. Min Act: -0.0001

Data Index: 1544095 (Python Code)

Max Activating Token Index: 376

Text #9

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2222. Min Act: -0.0000

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2135. Min Act: -0.0000

Data Index: 658008 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1901. Min Act: -0.0001

Data Index: 1513357 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1880. Min Act: -0.0000

Data Index: 230125 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1392009 (Python Code)

Max Activating Token Index: 717

Text #14

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1538574 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1238103 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1634774 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1595286 (Python Code)

Max Activating Token Index: 758

Text #18

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1541406 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1412667 (Python Code)

Max Activating Token Index: 579