Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 414 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6889. Min Act: -0.0000

Data Index: 111178 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1339068 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6228. Min Act: -0.0000

Data Index: 984987 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6383. Min Act: -0.0000

Data Index: 809587 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6154. Min Act: -0.0000

Data Index: 644745 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1638773 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.6039. Min Act: -0.0000

Data Index: 869887 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5899. Min Act: -0.0000

Data Index: 769139 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5835. Min Act: -0.0000

Data Index: 896180 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5424. Min Act: -0.0000

Data Index: 469156 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1049615 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1340799 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5584. Min Act: -0.0000

Data Index: 63515 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5496. Min Act: -0.0000

Data Index: 256420 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5678. Min Act: -0.0000

Data Index: 693618 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5079. Min Act: -0.0000

Data Index: 27770 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1012873 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1249880 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1012281 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.6889. Min Range: -0.6889

Max Act: 0.5389. Min Act: -0.0000

Data Index: 880798 (C4 (Web Text))

Max Activating Token Index: 905