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

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

Neuron 5965 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1645906 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1503539 (Python Code)

Max Activating Token Index: 805

Text #2

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1475256 (Python Code)

Max Activating Token Index: 310

Text #3

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1421127 (Python Code)

Max Activating Token Index: 583

Text #4

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1516735 (Python Code)

Max Activating Token Index: 1011

Text #5

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1451643 (Python Code)

Max Activating Token Index: 318

Text #6

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1402835 (Python Code)

Max Activating Token Index: 618

Text #7

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1499944 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1500410 (Python Code)

Max Activating Token Index: 144

Text #9

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1417461 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1384903 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1582894 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1369007 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1404110 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1645169 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1530859 (Python Code)

Max Activating Token Index: 506

Text #16

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1487870 (Python Code)

Max Activating Token Index: 830

Text #17

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1498841 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1414878 (Python Code)

Max Activating Token Index: 1008

Text #19

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1632273 (Python Code)

Max Activating Token Index: 950