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

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

Neuron 4161 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.1376. Min Act: -0.0001

Data Index: 1080379 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0040. Min Act: -0.0001

Data Index: 1342081 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.1376. Min Range: -1.1376

Max Act: 1.0668. Min Act: -0.0001

Data Index: 666215 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9852. Min Act: -0.0001

Data Index: 321227 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9788. Min Act: -0.0001

Data Index: 172417 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9444. Min Act: -0.0001

Data Index: 811240 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9773. Min Act: -0.0001

Data Index: 1063245 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8287. Min Act: -0.0001

Data Index: 611145 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9376. Min Act: -0.0001

Data Index: 1126090 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9176. Min Act: -0.0001

Data Index: 481237 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9098. Min Act: -0.0001

Data Index: 36820 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9270. Min Act: -0.0001

Data Index: 1006891 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8863. Min Act: -0.0000

Data Index: 730634 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9218. Min Act: -0.0001

Data Index: 415203 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8340. Min Act: -0.0000

Data Index: 56938 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.7502. Min Act: -0.0001

Data Index: 76032 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9020. Min Act: -0.0001

Data Index: 953943 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8672. Min Act: -0.0001

Data Index: 1113953 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.9352. Min Act: -0.0001

Data Index: 167337 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 1.1376. Min Range: -1.1376

Max Act: 0.8446. Min Act: -0.0001

Data Index: 618790 (C4 (Web Text))

Max Activating Token Index: 386