Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2798 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1525948 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1586782 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1650716 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1382113 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1374280 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1496899 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1507237 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8950. Min Act: -0.0002

Data Index: 1586659 (Python Code)

Max Activating Token Index: 566

Text #8

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8271. Min Act: -0.0002

Data Index: 1585937 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1533630 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1474717 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1461163 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1528557 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1454913 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1513099 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1442624 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1474886 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1453607 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1421140 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7904. Min Act: -0.0003

Data Index: 1487979 (Python Code)

Max Activating Token Index: 2