Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 490 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7566. Min Act: -0.0000

Data Index: 1401556 (Python Code)

Max Activating Token Index: 138

Text #1

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6534. Min Act: -0.0000

Data Index: 1583111 (Python Code)

Max Activating Token Index: 116

Text #2

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7185. Min Act: -0.0000

Data Index: 1476705 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7166. Min Act: -0.0000

Data Index: 1360537 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.5992. Min Act: -0.0000

Data Index: 1516783 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.5898. Min Act: -0.0000

Data Index: 1522232 (Python Code)

Max Activating Token Index: 667

Text #6

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6636. Min Act: -0.0000

Data Index: 1373746 (Python Code)

Max Activating Token Index: 867

Text #7

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1547029 (Python Code)

Max Activating Token Index: 972

Text #8

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1397765 (Python Code)

Max Activating Token Index: 882

Text #9

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.4594. Min Act: -0.0000

Data Index: 1630655 (Python Code)

Max Activating Token Index: 852

Text #10

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1413501 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1366797 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1483349 (Python Code)

Max Activating Token Index: 485

Text #13

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.2301. Min Act: -0.0000

Data Index: 1564738 (Python Code)

Max Activating Token Index: 730

Text #14

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1498848 (Python Code)

Max Activating Token Index: 935

Text #15

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.0467. Min Act: -0.0001

Data Index: 1561395 (Python Code)

Max Activating Token Index: 295

Text #16

Max Range: 1.7566. Min Range: -1.7566

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1007095 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 1.7566. Min Range: -1.7566

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1612699 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 1.7566. Min Range: -1.7566

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1546612 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 1.7566. Min Range: -1.7566

Max Act: 0.8535. Min Act: 0.0000

Data Index: 1478594 (Python Code)

Max Activating Token Index: 459