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

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

Neuron 3790 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8616. Min Range: -3.8616

Max Act: 3.8616. Min Act: -0.0000

Data Index: 1640965 (Python Code)

Max Activating Token Index: 217

Text #1

Max Range: 3.8616. Min Range: -3.8616

Max Act: 3.5699. Min Act: -0.0000

Data Index: 1577752 (Python Code)

Max Activating Token Index: 556

Text #2

Max Range: 3.8616. Min Range: -3.8616

Max Act: 3.0244. Min Act: -0.0000

Data Index: 1280897 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 3.8616. Min Range: -3.8616

Max Act: 3.0230. Min Act: -0.0000

Data Index: 1453069 (Python Code)

Max Activating Token Index: 534

Text #4

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.8416. Min Act: -0.0000

Data Index: 605313 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 3.8616. Min Range: -3.8616

Max Act: 3.0600. Min Act: -0.0000

Data Index: 1525684 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.7539. Min Act: -0.0000

Data Index: 1621382 (Python Code)

Max Activating Token Index: 99

Text #7

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.6833. Min Act: -0.0000

Data Index: 1505983 (Python Code)

Max Activating Token Index: 500

Text #8

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.7921. Min Act: -0.0000

Data Index: 1406567 (Python Code)

Max Activating Token Index: 522

Text #9

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.7910. Min Act: -0.0000

Data Index: 1513680 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.6068. Min Act: -0.0000

Data Index: 1562311 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.6031. Min Act: -0.0000

Data Index: 1339854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.8560. Min Act: -0.0000

Data Index: 1598896 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.7359. Min Act: -0.0000

Data Index: 1059928 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.7300. Min Act: -0.0000

Data Index: 233347 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.7141. Min Act: -0.0000

Data Index: 1067216 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.5909. Min Act: -0.0000

Data Index: 1508051 (Python Code)

Max Activating Token Index: 1004

Text #17

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.6860. Min Act: -0.0000

Data Index: 1376679 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.8197. Min Act: -0.0000

Data Index: 1490714 (Python Code)

Max Activating Token Index: 502

Text #19

Max Range: 3.8616. Min Range: -3.8616

Max Act: 2.6623. Min Act: -0.0000

Data Index: 1594991 (Python Code)

Max Activating Token Index: 123