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

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

Neuron 3766 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3780. Min Range: -3.3780

Max Act: 3.3708. Min Act: -0.0000

Data Index: 587054 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 3.3780. Min Range: -3.3780

Max Act: 3.3780. Min Act: -0.0000

Data Index: 232081 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 3.3780. Min Range: -3.3780

Max Act: 3.1119. Min Act: -0.0000

Data Index: 774054 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 3.3780. Min Range: -3.3780

Max Act: 3.1516. Min Act: -0.0000

Data Index: 1275023 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.6806. Min Act: -0.0000

Data Index: 378884 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.9463. Min Act: -0.0000

Data Index: 371421 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 3.3780. Min Range: -3.3780

Max Act: 3.0895. Min Act: -0.0000

Data Index: 1278252 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.7997. Min Act: -0.0000

Data Index: 258829 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.9391. Min Act: -0.0000

Data Index: 544691 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.9892. Min Act: -0.0000

Data Index: 1111270 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.8102. Min Act: -0.0000

Data Index: 764511 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.3780. Min Range: -3.3780

Max Act: 3.0930. Min Act: -0.0000

Data Index: 648979 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.9550. Min Act: -0.0000

Data Index: 1140444 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.9229. Min Act: -0.0000

Data Index: 116798 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.7604. Min Act: -0.0000

Data Index: 566365 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.8790. Min Act: -0.0000

Data Index: 115091 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.7428. Min Act: -0.0000

Data Index: 596289 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.8448. Min Act: -0.0000

Data Index: 1321264 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.7006. Min Act: -0.0000

Data Index: 303114 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.3780. Min Range: -3.3780

Max Act: 2.7852. Min Act: -0.0000

Data Index: 254330 (C4 (Web Text))

Max Activating Token Index: 729