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

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

Neuron 5290 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: 3.0121. Min Range: -3.0121

Max Act: 3.0121. Min Act: -0.0000

Data Index: 1540563 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.8083. Min Act: -0.0000

Data Index: 1378195 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.9072. Min Act: -0.0000

Data Index: 1460916 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.8674. Min Act: -0.0000

Data Index: 1546979 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.5730. Min Act: -0.0000

Data Index: 1570721 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.3235. Min Act: -0.0000

Data Index: 1634596 (Python Code)

Max Activating Token Index: 301

Text #6

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.3056. Min Act: -0.0000

Data Index: 1445924 (Python Code)

Max Activating Token Index: 284

Text #7

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.6692. Min Act: -0.0000

Data Index: 1617777 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.5382. Min Act: -0.0000

Data Index: 1555252 (Python Code)

Max Activating Token Index: 732

Text #9

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.6552. Min Act: -0.0000

Data Index: 1582000 (Python Code)

Max Activating Token Index: 845

Text #10

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.5398. Min Act: -0.0000

Data Index: 1644995 (Python Code)

Max Activating Token Index: 645

Text #11

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.4395. Min Act: -0.0000

Data Index: 1644764 (Python Code)

Max Activating Token Index: 586

Text #12

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.3137. Min Act: -0.0000

Data Index: 1573007 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.4301. Min Act: -0.0000

Data Index: 1447472 (Python Code)

Max Activating Token Index: 101

Text #14

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.3891. Min Act: -0.0000

Data Index: 1468611 (Python Code)

Max Activating Token Index: 368

Text #15

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.7882. Min Act: -0.0000

Data Index: 1488401 (Python Code)

Max Activating Token Index: 353

Text #16

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.3850. Min Act: -0.0000

Data Index: 1546375 (Python Code)

Max Activating Token Index: 438

Text #17

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.3734. Min Act: -0.0000

Data Index: 1377117 (Python Code)

Max Activating Token Index: 489

Text #18

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.3604. Min Act: -0.0000

Data Index: 1569652 (Python Code)

Max Activating Token Index: 130

Text #19

Max Range: 3.0121. Min Range: -3.0121

Max Act: 2.2337. Min Act: -0.0000

Data Index: 1460946 (Python Code)

Max Activating Token Index: 118