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

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

Neuron 954 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: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1253664 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1469083 (Python Code)

Max Activating Token Index: 1000

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0005

Data Index: 408257 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1601462 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1619464 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1565380 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1459203 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0006

Data Index: 273567 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1439513 (Python Code)

Max Activating Token Index: 694

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1504139 (Python Code)

Max Activating Token Index: 953

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0005

Data Index: 288643 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1364515 (Python Code)

Max Activating Token Index: 562

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0051. Min Act: -0.0006

Data Index: 483405 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0005

Data Index: 422017 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1481208 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1009321 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0006

Data Index: 763139 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1380263 (Python Code)

Max Activating Token Index: 621

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1474501 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1563564 (Python Code)

Max Activating Token Index: 28