Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 307 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0876. Min Act: -0.0005

Data Index: 1368412 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0005

Data Index: 1434715 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0760. Min Act: -0.0005

Data Index: 282643 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0695. Min Act: -0.0005

Data Index: 1517791 (Python Code)

Max Activating Token Index: 828

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0703. Min Act: -0.0005

Data Index: 1492056 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0647. Min Act: -0.0005

Data Index: 785016 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0678. Min Act: -0.0005

Data Index: 128796 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0682. Min Act: -0.0005

Data Index: 1512201 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0642. Min Act: -0.0005

Data Index: 999457 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0658. Min Act: -0.0004

Data Index: 50393 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0686. Min Act: -0.0005

Data Index: 1505514 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0686. Min Act: -0.0005

Data Index: 1555744 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0657. Min Act: -0.0005

Data Index: 1553585 (Python Code)

Max Activating Token Index: 920

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0630. Min Act: -0.0005

Data Index: 456989 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0695. Min Act: -0.0005

Data Index: 1300768 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0664. Min Act: -0.0005

Data Index: 1416768 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0656. Min Act: -0.0005

Data Index: 713003 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0665. Min Act: -0.0005

Data Index: 1640646 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0648. Min Act: -0.0005

Data Index: 830913 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0671. Min Act: -0.0005

Data Index: 967425 (C4 (Web Text))

Max Activating Token Index: 881