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

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

Neuron 3952 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: 0.0933. Min Range: -0.0933

Max Act: 0.0910. Min Act: -0.0003

Data Index: 1452915 (Python Code)

Max Activating Token Index: 108

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0003

Data Index: 1605076 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0875. Min Act: -0.0003

Data Index: 1467823 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0887. Min Act: -0.0003

Data Index: 1646591 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1449846 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1360076 (Python Code)

Max Activating Token Index: 693

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1639125 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1434189 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1485678 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0785. Min Act: -0.0003

Data Index: 1617930 (Python Code)

Max Activating Token Index: 182

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0806. Min Act: -0.0004

Data Index: 1553977 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1370594 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0778. Min Act: -0.0004

Data Index: 1564006 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1394407 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0822. Min Act: -0.0004

Data Index: 1435096 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1623324 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1635783 (Python Code)

Max Activating Token Index: 991

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0754. Min Act: -0.0004

Data Index: 1606511 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0726. Min Act: -0.0003

Data Index: 1637120 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1423428 (Python Code)

Max Activating Token Index: 563