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

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

Neuron 83 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.6347. Min Act: -0.0002

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5724. Min Act: -0.0001

Data Index: 82366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5295. Min Act: 0.0000

Data Index: 580283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5095. Min Act: -0.0001

Data Index: 1557800 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4966. Min Act: 0.0000

Data Index: 701218 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4899. Min Act: -0.0001

Data Index: 1406584 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4574. Min Act: -0.0001

Data Index: 1517888 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4566. Min Act: -0.0001

Data Index: 449476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4615. Min Act: -0.0002

Data Index: 1521263 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1176788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4261. Min Act: -0.0001

Data Index: 1647722 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4139. Min Act: 0.0001

Data Index: 335531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4033. Min Act: -0.0002

Data Index: 859150 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1601131 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3944. Min Act: -0.0002

Data Index: 132268 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3994. Min Act: -0.0001

Data Index: 1548359 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3964. Min Act: -0.0001

Data Index: 913058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3847. Min Act: -0.0002

Data Index: 1531712 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3892. Min Act: -0.0002

Data Index: 336395 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3756. Min Act: -0.0001

Data Index: 991572 (C4 (Web Text))

Max Activating Token Index: 1023