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

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

Neuron 411 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: 1.9550. Min Range: -1.9550

Max Act: 1.8665. Min Act: -0.0000

Data Index: 1393090 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.9355. Min Act: -0.0000

Data Index: 1556294 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6515. Min Act: -0.0000

Data Index: 1445626 (Python Code)

Max Activating Token Index: 307

Text #3

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.9550. Min Act: -0.0000

Data Index: 1569949 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1600472 (Python Code)

Max Activating Token Index: 696

Text #5

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8387. Min Act: -0.0000

Data Index: 1651651 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6222. Min Act: -0.0000

Data Index: 1406005 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1646385 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6096. Min Act: -0.0000

Data Index: 1365413 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.7574. Min Act: -0.0000

Data Index: 1513560 (Python Code)

Max Activating Token Index: 388

Text #10

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6983. Min Act: -0.0000

Data Index: 1525416 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6478. Min Act: -0.0000

Data Index: 1439264 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8945. Min Act: -0.0000

Data Index: 1563115 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1440434 (Python Code)

Max Activating Token Index: 804

Text #14

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.4734. Min Act: -0.0000

Data Index: 1584928 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6069. Min Act: -0.0000

Data Index: 1395563 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6086. Min Act: -0.0000

Data Index: 1522084 (Python Code)

Max Activating Token Index: 591

Text #17

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.6015. Min Act: -0.0000

Data Index: 1538917 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1546523 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1519261 (Python Code)

Max Activating Token Index: 509