Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 941 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1422862 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1454029 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1417860 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1310064 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0053. Min Act: -0.0006

Data Index: 854990 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1362187 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1362029 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1362241 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1363110 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1362651 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1362754 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1360815 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1362627 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1362869 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1362269 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1360175 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1363376 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1362250 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1360688 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1361719 (Python Code)

Max Activating Token Index: 1