Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1815 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1545594 (Python Code)

Max Activating Token Index: 696

Text #1

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0005

Data Index: 851483 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1598777 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1051925 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0005

Data Index: 944002 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1430285 (Python Code)

Max Activating Token Index: 660

Text #6

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1264464 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1551393 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1648671 (Python Code)

Max Activating Token Index: 648

Text #9

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1435165 (Python Code)

Max Activating Token Index: 189

Text #10

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0056. Min Act: -0.0005

Data Index: 275634 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1603673 (Python Code)

Max Activating Token Index: 559

Text #12

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0005

Data Index: 636082 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1438210 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0054. Min Act: -0.0005

Data Index: 291721 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1494178 (Python Code)

Max Activating Token Index: 745

Text #16

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0054. Min Act: -0.0005

Data Index: 145766 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1637704 (Python Code)

Max Activating Token Index: 874

Text #18

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0053. Min Act: -0.0006

Data Index: 958342 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.0062. Min Range: -0.0062

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1506755 (Python Code)

Max Activating Token Index: 456