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

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

Neuron 2456 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: 1.0129. Min Range: -1.0129

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1369896 (Python Code)

Max Activating Token Index: 698

Text #1

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.9348. Min Act: -0.0000

Data Index: 297351 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1445491 (Python Code)

Max Activating Token Index: 588

Text #3

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.8902. Min Act: -0.0000

Data Index: 481957 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1560409 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1412028 (Python Code)

Max Activating Token Index: 507

Text #6

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7761. Min Act: -0.0000

Data Index: 355128 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1401665 (Python Code)

Max Activating Token Index: 443

Text #8

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1471515 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1422110 (Python Code)

Max Activating Token Index: 325

Text #10

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1380907 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1496477 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1414527 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7150. Min Act: -0.0000

Data Index: 89695 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7269. Min Act: -0.0000

Data Index: 686683 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1454922 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1184396 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7013. Min Act: -0.0000

Data Index: 250230 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.7679. Min Act: -0.0000

Data Index: 92328 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.0129. Min Range: -1.0129

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1144604 (C4 (Web Text))

Max Activating Token Index: 627