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

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

Neuron 4815 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1743. Min Range: -2.1743

Max Act: 2.1743. Min Act: -0.0000

Data Index: 1439929 (Python Code)

Max Activating Token Index: 569

Text #1

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.9967. Min Act: -0.0000

Data Index: 1412700 (Python Code)

Max Activating Token Index: 639

Text #2

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.7835. Min Act: -0.0000

Data Index: 1510519 (Python Code)

Max Activating Token Index: 728

Text #3

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.6915. Min Act: -0.0000

Data Index: 1594672 (Python Code)

Max Activating Token Index: 660

Text #4

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.6088. Min Act: -0.0000

Data Index: 1375470 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1475737 (Python Code)

Max Activating Token Index: 135

Text #6

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.3757. Min Act: -0.0000

Data Index: 1637422 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1557295 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.2660. Min Act: -0.0001

Data Index: 1506010 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1648474 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1393777 (Python Code)

Max Activating Token Index: 203

Text #11

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1418895 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1516205 (Python Code)

Max Activating Token Index: 415

Text #13

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1611512 (Python Code)

Max Activating Token Index: 160

Text #14

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1473502 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1361421 (Python Code)

Max Activating Token Index: 733

Text #16

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1399317 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.2479. Min Act: -0.0000

Data Index: 1531997 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.4131. Min Act: -0.0000

Data Index: 1642525 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1444390 (Python Code)

Max Activating Token Index: 707