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

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

Neuron 5790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1644993 (Python Code)

Max Activating Token Index: 969

Text #1

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.7194. Min Act: -0.0000

Data Index: 919771 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1366672 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1588909 (Python Code)

Max Activating Token Index: 668

Text #4

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.7066. Min Act: -0.0000

Data Index: 121156 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1363219 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1464514 (Python Code)

Max Activating Token Index: 988

Text #7

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1438159 (Python Code)

Max Activating Token Index: 412

Text #8

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1418332 (Python Code)

Max Activating Token Index: 987

Text #9

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1383163 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1527717 (Python Code)

Max Activating Token Index: 208

Text #11

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1372663 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1137746 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1510181 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1559655 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1426403 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1529434 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1509514 (Python Code)

Max Activating Token Index: 571

Text #18

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.5464. Min Act: -0.0000

Data Index: 245576 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.7725. Min Range: -0.7725

Max Act: 0.5615. Min Act: -0.0000

Data Index: 910463 (C4 (Web Text))

Max Activating Token Index: 426