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

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

Neuron 4246 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.3616. Min Act: -0.0000

Data Index: 581543 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.1640. Min Act: -0.0000

Data Index: 363738 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.0671. Min Act: -0.0000

Data Index: 1217042 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.3077. Min Act: -0.0000

Data Index: 516818 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1205236 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9095. Min Act: -0.0000

Data Index: 640313 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8753. Min Act: -0.0000

Data Index: 105415 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7319. Min Act: -0.0000

Data Index: 316091 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8343. Min Act: -0.0000

Data Index: 53047 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7473. Min Act: -0.0000

Data Index: 998333 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8095. Min Act: -0.0000

Data Index: 602501 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1309088 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7227. Min Act: -0.0000

Data Index: 718314 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7259. Min Act: -0.0000

Data Index: 473188 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1156624 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.6324. Min Act: -0.0000

Data Index: 2222 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1192911 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1144190 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.6792. Min Act: -0.0000

Data Index: 506217 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.6212. Min Act: -0.0000

Data Index: 315545 (C4 (Web Text))

Max Activating Token Index: 538