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

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

Neuron 289 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3854. Min Range: -2.3854

Max Act: 2.3854. Min Act: -0.0000

Data Index: 180226 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 2.3854. Min Range: -2.3854

Max Act: 2.2431. Min Act: -0.0000

Data Index: 946267 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 2.3854. Min Range: -2.3854

Max Act: 2.0620. Min Act: -0.0000

Data Index: 745288 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.9820. Min Act: -0.0000

Data Index: 959933 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 2.3854. Min Range: -2.3854

Max Act: 2.1868. Min Act: -0.0000

Data Index: 749395 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.8331. Min Act: -0.0000

Data Index: 940352 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 2.3854. Min Range: -2.3854

Max Act: 2.1615. Min Act: -0.0000

Data Index: 466931 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.9436. Min Act: -0.0000

Data Index: 940512 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 2.3854. Min Range: -2.3854

Max Act: 2.1344. Min Act: -0.0000

Data Index: 203962 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.7966. Min Act: -0.0000

Data Index: 415246 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.8920. Min Act: -0.0000

Data Index: 574356 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.9809. Min Act: -0.0000

Data Index: 608445 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.8081. Min Act: -0.0000

Data Index: 1348768 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.7362. Min Act: -0.0000

Data Index: 1132540 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.7858. Min Act: -0.0000

Data Index: 373370 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.7452. Min Act: -0.0000

Data Index: 1140265 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.7590. Min Act: -0.0000

Data Index: 780753 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.8625. Min Act: -0.0000

Data Index: 225068 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.6640. Min Act: -0.0000

Data Index: 505490 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 2.3854. Min Range: -2.3854

Max Act: 1.6337. Min Act: -0.0000

Data Index: 1086675 (C4 (Web Text))

Max Activating Token Index: 527