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

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

Neuron 273 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: 5.0172. Min Range: -5.0172

Max Act: 5.0172. Min Act: -0.0000

Data Index: 955266 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 5.0172. Min Range: -5.0172

Max Act: 4.1181. Min Act: -0.0000

Data Index: 1518077 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 5.0172. Min Range: -5.0172

Max Act: 4.2035. Min Act: -0.0000

Data Index: 1385580 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.8899. Min Act: -0.0000

Data Index: 1423878 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.3142. Min Act: -0.0000

Data Index: 28202 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.6661. Min Act: -0.0000

Data Index: 1514196 (Python Code)

Max Activating Token Index: 271

Text #6

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.4732. Min Act: -0.0000

Data Index: 1288507 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.1723. Min Act: -0.0000

Data Index: 1571486 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.4975. Min Act: -0.0000

Data Index: 773584 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.1362. Min Act: -0.0000

Data Index: 464353 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.0999. Min Act: -0.0000

Data Index: 1445512 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.3744. Min Act: -0.0000

Data Index: 1407169 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.3933. Min Act: -0.0000

Data Index: 792357 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.1829. Min Act: -0.0000

Data Index: 1351070 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.1600. Min Act: -0.0000

Data Index: 322144 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.2862. Min Act: -0.0000

Data Index: 955129 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.1086. Min Act: -0.0000

Data Index: 908162 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 5.0172. Min Range: -5.0172

Max Act: 3.1058. Min Act: -0.0000

Data Index: 1653005 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 5.0172. Min Range: -5.0172

Max Act: 2.9751. Min Act: -0.0000

Data Index: 1618078 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 5.0172. Min Range: -5.0172

Max Act: 2.9392. Min Act: -0.0000

Data Index: 730443 (C4 (Web Text))

Max Activating Token Index: 34