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

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

Neuron 3943 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.6992. Min Act: -0.0000

Data Index: 1549177 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1489883 (Python Code)

Max Activating Token Index: 401

Text #2

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1498083 (Python Code)

Max Activating Token Index: 278

Text #3

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.2395. Min Act: -0.0000

Data Index: 520667 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1498958 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1466174 (Python Code)

Max Activating Token Index: 753

Text #6

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1504511 (Python Code)

Max Activating Token Index: 326

Text #7

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1644210 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1775. Min Act: 0.0000

Data Index: 1557042 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1471947 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.2551. Min Act: -0.0000

Data Index: 1588083 (Python Code)

Max Activating Token Index: 359

Text #11

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1507598 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1926. Min Act: -0.0000

Data Index: 1420326 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1566. Min Act: -0.0000

Data Index: 1389086 (Python Code)

Max Activating Token Index: 167

Text #14

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1507268 (Python Code)

Max Activating Token Index: 956

Text #15

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1138. Min Act: -0.0000

Data Index: 180022 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1651440 (Python Code)

Max Activating Token Index: 821

Text #17

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.1063. Min Act: -0.0000

Data Index: 530592 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1427748 (Python Code)

Max Activating Token Index: 255

Text #19

Max Range: 1.6992. Min Range: -1.6992

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1475276 (Python Code)

Max Activating Token Index: 849