Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5625 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.8750. Min Act: -0.0000

Data Index: 932986 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.9843. Min Act: -0.0000

Data Index: 48936 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.7700. Min Act: -0.0000

Data Index: 979166 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1189771 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.6719. Min Act: -0.0000

Data Index: 444861 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.6763. Min Act: -0.0000

Data Index: 514484 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1207342 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.6960. Min Act: -0.0000

Data Index: 72288 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1179095 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.6208. Min Act: -0.0000

Data Index: 799138 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5950. Min Act: -0.0000

Data Index: 290848 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5831. Min Act: -0.0000

Data Index: 389191 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5972. Min Act: -0.0000

Data Index: 313802 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5795. Min Act: -0.0000

Data Index: 711987 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5380. Min Act: -0.0000

Data Index: 423860 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5848. Min Act: -0.0000

Data Index: 158100 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1108903 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5633. Min Act: -0.0000

Data Index: 201283 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5403. Min Act: -0.0000

Data Index: 491867 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.9843. Min Range: -0.9843

Max Act: 0.5131. Min Act: -0.0000

Data Index: 39933 (C4 (Web Text))

Max Activating Token Index: 545