Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5992. Min Act: -0.0002

Data Index: 253961 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4867. Min Act: -0.0002

Data Index: 1510367 (Python Code)

Max Activating Token Index: 264

Text #2

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5546. Min Act: -0.0002

Data Index: 286016 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5035. Min Act: -0.0002

Data Index: 1003239 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5354. Min Act: -0.0002

Data Index: 672687 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5295. Min Act: -0.0002

Data Index: 992612 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4796. Min Act: -0.0002

Data Index: 68667 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5124. Min Act: -0.0002

Data Index: 422388 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5067. Min Act: -0.0002

Data Index: 992975 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5031. Min Act: -0.0002

Data Index: 176979 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5028. Min Act: -0.0002

Data Index: 1026786 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5357. Min Act: -0.0002

Data Index: 384120 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4804. Min Act: -0.0002

Data Index: 282825 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4484. Min Act: -0.0002

Data Index: 1129295 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5113. Min Act: -0.0002

Data Index: 237673 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5087. Min Act: -0.0002

Data Index: 317024 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5271. Min Act: -0.0002

Data Index: 760597 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4925. Min Act: -0.0002

Data Index: 157939 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5245. Min Act: -0.0002

Data Index: 327552 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5086. Min Act: -0.0002

Data Index: 500281 (C4 (Web Text))

Max Activating Token Index: 419