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

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

Neuron 630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9285. Min Range: -3.9285

Max Act: 3.9285. Min Act: -0.0001

Data Index: 622281 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 3.9285. Min Range: -3.9285

Max Act: 3.4155. Min Act: -0.0000

Data Index: 840402 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 3.9285. Min Range: -3.9285

Max Act: 2.5897. Min Act: -0.0000

Data Index: 864951 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.9285. Min Range: -3.9285

Max Act: 3.3231. Min Act: -0.0000

Data Index: 1143627 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.9955. Min Act: -0.0000

Data Index: 364291 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 3.9285. Min Range: -3.9285

Max Act: 2.3903. Min Act: -0.0000

Data Index: 357978 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.9211. Min Act: -0.0000

Data Index: 277532 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 3.9285. Min Range: -3.9285

Max Act: 2.1099. Min Act: -0.0001

Data Index: 40975 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.8596. Min Act: -0.0001

Data Index: 402436 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.5567. Min Act: -0.0001

Data Index: 833457 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.8519. Min Act: -0.0000

Data Index: 565145 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 3.9285. Min Range: -3.9285

Max Act: 2.5656. Min Act: -0.0001

Data Index: 1326697 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.8319. Min Act: -0.0000

Data Index: 842148 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.8170. Min Act: -0.0000

Data Index: 640262 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.8493. Min Act: -0.0000

Data Index: 19273 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.7522. Min Act: -0.0001

Data Index: 427842 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.6565. Min Act: -0.0001

Data Index: 459268 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.5891. Min Act: -0.0001

Data Index: 257861 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.6765. Min Act: -0.0000

Data Index: 574406 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.9285. Min Range: -3.9285

Max Act: 1.6761. Min Act: -0.0001

Data Index: 52426 (C4 (Web Text))

Max Activating Token Index: 499