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

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

Neuron 2976 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1559. Min Range: -2.1559

Max Act: 2.1559. Min Act: -0.0000

Data Index: 1509633 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 2.1559. Min Range: -2.1559

Max Act: 2.0333. Min Act: -0.0000

Data Index: 1453967 (Python Code)

Max Activating Token Index: 498

Text #2

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.1791. Min Act: -0.0000

Data Index: 1619593 (Python Code)

Max Activating Token Index: 778

Text #3

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.0536. Min Act: -0.0000

Data Index: 1397755 (Python Code)

Max Activating Token Index: 673

Text #4

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1455678 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.1685. Min Act: -0.0000

Data Index: 1400972 (Python Code)

Max Activating Token Index: 244

Text #6

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1531965 (Python Code)

Max Activating Token Index: 761

Text #7

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1629143 (Python Code)

Max Activating Token Index: 966

Text #8

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1636928 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.1927. Min Act: -0.0000

Data Index: 1365555 (Python Code)

Max Activating Token Index: 568

Text #10

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1492348 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1526732 (Python Code)

Max Activating Token Index: 857

Text #12

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1653299 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 2.1559. Min Range: -2.1559

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1499329 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1363374 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1484194 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 2.1559. Min Range: -2.1559

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1412817 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1395432 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 2.1559. Min Range: -2.1559

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1572114 (Python Code)

Max Activating Token Index: 171

Text #19

Max Range: 2.1559. Min Range: -2.1559

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1361514 (Python Code)

Max Activating Token Index: 641