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

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

Neuron 4794 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: 2.5379. Min Range: -2.5379

Max Act: 2.5379. Min Act: -0.0000

Data Index: 217773 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 2.5379. Min Range: -2.5379

Max Act: 2.4166. Min Act: -0.0000

Data Index: 645767 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 2.5379. Min Range: -2.5379

Max Act: 2.1781. Min Act: -0.0000

Data Index: 174972 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 2.5379. Min Range: -2.5379

Max Act: 2.2252. Min Act: -0.0000

Data Index: 1259704 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 2.5379. Min Range: -2.5379

Max Act: 2.0948. Min Act: -0.0000

Data Index: 312027 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.9695. Min Act: -0.0000

Data Index: 682131 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.9987. Min Act: -0.0000

Data Index: 964758 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.8630. Min Act: -0.0000

Data Index: 287127 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.9470. Min Act: -0.0000

Data Index: 409467 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.9424. Min Act: -0.0000

Data Index: 875738 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.9013. Min Act: -0.0000

Data Index: 237716 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.7468. Min Act: -0.0000

Data Index: 356058 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.8282. Min Act: -0.0000

Data Index: 797102 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.8173. Min Act: -0.0000

Data Index: 583723 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.7123. Min Act: -0.0000

Data Index: 423692 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.7743. Min Act: -0.0000

Data Index: 953262 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.7732. Min Act: -0.0000

Data Index: 1127623 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.5918. Min Act: -0.0000

Data Index: 377509 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.7572. Min Act: -0.0000

Data Index: 954965 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 2.5379. Min Range: -2.5379

Max Act: 1.7555. Min Act: -0.0000

Data Index: 122212 (C4 (Web Text))

Max Activating Token Index: 623