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

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

Neuron 666 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1590617 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1545690 (Python Code)

Max Activating Token Index: 293

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1615116 (Python Code)

Max Activating Token Index: 455

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1575017 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1505343 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1455035 (Python Code)

Max Activating Token Index: 199

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1395934 (Python Code)

Max Activating Token Index: 527

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1610364 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1394173 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1421870 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1406786 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1386597 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1583160 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1595981 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1550449 (Python Code)

Max Activating Token Index: 205

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1560998 (Python Code)

Max Activating Token Index: 475

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1460831 (Python Code)

Max Activating Token Index: 128

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1374127 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1625103 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1583871 (Python Code)

Max Activating Token Index: 659