Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2117 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1417677 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1627818 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1624954 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1623084 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1614935 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1594768 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1587540 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1585527 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1375628 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1575433 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1562323 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1557800 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1545190 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1537516 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1527500 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1510891 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1498917 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1480400 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1452229 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1437168 (Python Code)

Max Activating Token Index: 1