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

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

Neuron 3987 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1625491 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1438625 (Python Code)

Max Activating Token Index: 748

Text #2

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1332108 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1540327 (Python Code)

Max Activating Token Index: 391

Text #4

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1451646 (Python Code)

Max Activating Token Index: 241

Text #5

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1532405 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1577476 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1498372 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1452083 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3351. Min Act: -0.0000

Data Index: 255384 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1533725 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3433. Min Act: -0.0000

Data Index: 987398 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1260877 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1503860 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3071. Min Act: -0.0000

Data Index: 843101 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3156. Min Act: -0.0000

Data Index: 739553 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1310453 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1498698 (Python Code)

Max Activating Token Index: 286

Text #18

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1507579 (Python Code)

Max Activating Token Index: 320

Text #19

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3067. Min Act: -0.0000

Data Index: 413158 (C4 (Web Text))

Max Activating Token Index: 57