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

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

Neuron 1603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2196. Min Range: -1.2196

Max Act: 1.2196. Min Act: -0.0000

Data Index: 242095 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8691. Min Act: -0.0001

Data Index: 1342690 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8864. Min Act: -0.0000

Data Index: 475916 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1372005 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7784. Min Act: -0.0000

Data Index: 94876 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1420487 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1462086 (Python Code)

Max Activating Token Index: 859

Text #7

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1100219 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1543009 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6237. Min Act: -0.0000

Data Index: 322176 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6634. Min Act: -0.0000

Data Index: 984756 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6628. Min Act: -0.0000

Data Index: 498432 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6522. Min Act: -0.0000

Data Index: 939465 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6320. Min Act: -0.0000

Data Index: 547863 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1620307 (Python Code)

Max Activating Token Index: 496

Text #15

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6056. Min Act: -0.0000

Data Index: 550573 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1458964 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6094. Min Act: -0.0000

Data Index: 686502 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1266289 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.6039. Min Act: -0.0000

Data Index: 678588 (C4 (Web Text))

Max Activating Token Index: 661