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

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

Neuron 3236 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4415. Min Act: -0.0000

Data Index: 712906 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4458. Min Act: -0.0000

Data Index: 659661 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1502007 (Python Code)

Max Activating Token Index: 1014

Text #3

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1297612 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1484340 (Python Code)

Max Activating Token Index: 1011

Text #5

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1386988 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1486584 (Python Code)

Max Activating Token Index: 879

Text #7

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1410255 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1443045 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1394385 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1433610 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1267861 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1468434 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1477722 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1571712 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1548367 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1640377 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3803. Min Act: -0.0000

Data Index: 356328 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1440422 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1542589 (Python Code)

Max Activating Token Index: 990