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

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

Neuron 251 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.7686. Min Act: -0.0000

Data Index: 74295 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6445. Min Act: -0.0000

Data Index: 659753 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6391. Min Act: -0.0000

Data Index: 330891 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6133. Min Act: -0.0000

Data Index: 668826 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1284118 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6620. Min Act: -0.0000

Data Index: 926541 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6596. Min Act: -0.0000

Data Index: 666589 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.8539. Min Act: -0.0000

Data Index: 1160548 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 2.0001. Min Range: -2.0001

Max Act: 2.0001. Min Act: -0.0000

Data Index: 978888 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6101. Min Act: -0.0000

Data Index: 1357907 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6106. Min Act: -0.0000

Data Index: 1003606 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5974. Min Act: -0.0000

Data Index: 688841 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5989. Min Act: -0.0000

Data Index: 1251216 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5023. Min Act: -0.0000

Data Index: 127211 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5931. Min Act: -0.0000

Data Index: 991563 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6807. Min Act: -0.0000

Data Index: 1289849 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5536. Min Act: -0.0000

Data Index: 75670 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6405. Min Act: -0.0000

Data Index: 475097 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5494. Min Act: -0.0000

Data Index: 152722 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5150. Min Act: -0.0000

Data Index: 309737 (C4 (Web Text))

Max Activating Token Index: 551