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

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

Neuron 5600 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: 3.4504. Min Range: -3.4504

Max Act: 3.4504. Min Act: -0.0001

Data Index: 1118798 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 3.4504. Min Range: -3.4504

Max Act: 3.2062. Min Act: -0.0001

Data Index: 114646 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 3.4504. Min Range: -3.4504

Max Act: 3.2185. Min Act: -0.0001

Data Index: 223925 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 3.4504. Min Range: -3.4504

Max Act: 3.1222. Min Act: -0.0000

Data Index: 662915 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.5823. Min Act: -0.0000

Data Index: 456015 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.5760. Min Act: -0.0000

Data Index: 853873 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.6922. Min Act: -0.0000

Data Index: 1352438 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.6480. Min Act: -0.0001

Data Index: 791578 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.5170. Min Act: -0.0001

Data Index: 286092 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.3728. Min Act: -0.0000

Data Index: 1295427 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.4080. Min Act: -0.0000

Data Index: 1198585 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.3753. Min Act: -0.0001

Data Index: 1111172 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.4733. Min Act: -0.0001

Data Index: 1278387 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.4449. Min Act: -0.0001

Data Index: 1112326 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.4383. Min Act: -0.0001

Data Index: 49210 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.4440. Min Act: -0.0001

Data Index: 766324 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.5522. Min Act: -0.0001

Data Index: 3364 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.2843. Min Act: -0.0001

Data Index: 114034 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.3612. Min Act: -0.0001

Data Index: 1222956 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.1294. Min Act: -0.0001

Data Index: 164334 (C4 (Web Text))

Max Activating Token Index: 832