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

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

Neuron 2906 in Layer 1

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: 0.0833. Min Range: -0.0833

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1458670 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1464250 (Python Code)

Max Activating Token Index: 452

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1509265 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1541402 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1640200 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1513425 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1387102 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1552764 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1497051 (Python Code)

Max Activating Token Index: 466

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1422874 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1552650 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1536824 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1425991 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1421740 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1379571 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1627628 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1616393 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1538670 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1629641 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1596787 (Python Code)

Max Activating Token Index: 3