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

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

Neuron 158 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.6256. Min Act: -0.0002

Data Index: 733475 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.5796. Min Act: -0.0002

Data Index: 980863 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.6069. Min Act: -0.0002

Data Index: 1075911 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4997. Min Act: -0.0002

Data Index: 1337451 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.5037. Min Act: -0.0002

Data Index: 285571 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.5154. Min Act: -0.0002

Data Index: 3720 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4787. Min Act: -0.0002

Data Index: 1292442 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4040. Min Act: -0.0002

Data Index: 392394 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4021. Min Act: -0.0002

Data Index: 884104 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4344. Min Act: -0.0002

Data Index: 186386 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4209. Min Act: -0.0002

Data Index: 1261202 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.4099. Min Act: -0.0002

Data Index: 327398 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3656. Min Act: -0.0002

Data Index: 422254 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3567. Min Act: -0.0002

Data Index: 811584 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3842. Min Act: -0.0002

Data Index: 158305 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3555. Min Act: -0.0002

Data Index: 396225 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3496. Min Act: -0.0002

Data Index: 403631 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3639. Min Act: -0.0003

Data Index: 1000414 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3837. Min Act: -0.0002

Data Index: 856012 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.6256. Min Range: -1.6256

Max Act: 1.3446. Min Act: -0.0002

Data Index: 454599 (C4 (Web Text))

Max Activating Token Index: 868