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

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

Neuron 4593 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3790. Min Range: -2.3790

Max Act: 2.2985. Min Act: -0.0000

Data Index: 126960 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 2.3790. Min Range: -2.3790

Max Act: 2.3790. Min Act: -0.0000

Data Index: 172291 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.7404. Min Act: -0.0000

Data Index: 1085274 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.7036. Min Act: -0.0000

Data Index: 927105 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1057293 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.6488. Min Act: -0.0000

Data Index: 60079 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4271. Min Act: -0.0000

Data Index: 402458 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.3950. Min Act: -0.0000

Data Index: 58398 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.5842. Min Act: -0.0000

Data Index: 7109 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1119008 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4370. Min Act: -0.0000

Data Index: 361715 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.3603. Min Act: -0.0000

Data Index: 106028 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4337. Min Act: -0.0000

Data Index: 305482 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1049889 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4101. Min Act: -0.0000

Data Index: 345267 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1078306 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.5074. Min Act: -0.0000

Data Index: 1251071 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4959. Min Act: -0.0000

Data Index: 437439 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.3951. Min Act: -0.0000

Data Index: 185577 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 2.3790. Min Range: -2.3790

Max Act: 1.4788. Min Act: -0.0000

Data Index: 242696 (C4 (Web Text))

Max Activating Token Index: 699