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

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

Neuron 3547 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: 2.5901. Min Range: -2.5901

Max Act: 2.5901. Min Act: -0.0000

Data Index: 433454 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.4268. Min Act: -0.0000

Data Index: 1321721 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.1116. Min Act: -0.0000

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.2256. Min Act: -0.0000

Data Index: 412396 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.1706. Min Act: -0.0000

Data Index: 900159 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.3842. Min Act: -0.0000

Data Index: 1308997 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.1416. Min Act: -0.0000

Data Index: 451128 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.1339. Min Act: -0.0000

Data Index: 1047033 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.2139. Min Act: -0.0000

Data Index: 646814 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.1037. Min Act: -0.0000

Data Index: 864217 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.0674. Min Act: -0.0000

Data Index: 1170366 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.1698. Min Act: -0.0000

Data Index: 1270558 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 2.5901. Min Range: -2.5901

Max Act: 1.9218. Min Act: -0.0000

Data Index: 1178142 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 2.5901. Min Range: -2.5901

Max Act: 1.8143. Min Act: -0.0000

Data Index: 176926 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 2.5901. Min Range: -2.5901

Max Act: 1.8132. Min Act: -0.0000

Data Index: 633858 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 2.5901. Min Range: -2.5901

Max Act: 1.8040. Min Act: -0.0000

Data Index: 964300 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 2.5901. Min Range: -2.5901

Max Act: 1.8115. Min Act: -0.0000

Data Index: 256424 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 2.5901. Min Range: -2.5901

Max Act: 1.7998. Min Act: -0.0000

Data Index: 190678 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.5901. Min Range: -2.5901

Max Act: 2.1032. Min Act: -0.0000

Data Index: 39660 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 2.5901. Min Range: -2.5901

Max Act: 1.8745. Min Act: -0.0000

Data Index: 475426 (C4 (Web Text))

Max Activating Token Index: 24