Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2377 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0727. Min Act: -0.0003

Data Index: 1446607 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1399869 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1647685 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1527007 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1589866 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1555653 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1478051 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0627. Min Act: -0.0004

Data Index: 1568028 (Python Code)

Max Activating Token Index: 66

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1456723 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1361033 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1383345 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1490544 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1578193 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1550563 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1610232 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1650188 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1509908 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1549706 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1505649 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1452933 (Python Code)

Max Activating Token Index: 825