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

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

Neuron 4426 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8485. Min Range: -5.8485

Max Act: 5.6466. Min Act: -0.0000

Data Index: 1242889 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 5.8485. Min Range: -5.8485

Max Act: 5.8485. Min Act: -0.0000

Data Index: 721510 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 5.8485. Min Range: -5.8485

Max Act: 5.2077. Min Act: -0.0000

Data Index: 384015 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 5.8485. Min Range: -5.8485

Max Act: 5.6346. Min Act: -0.0000

Data Index: 855279 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.7609. Min Act: -0.0000

Data Index: 342574 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.8001. Min Act: -0.0000

Data Index: 264749 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 5.8485. Min Range: -5.8485

Max Act: 5.5839. Min Act: -0.0000

Data Index: 603887 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.5234. Min Act: -0.0000

Data Index: 453202 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.5110. Min Act: -0.0000

Data Index: 1206784 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.1744. Min Act: -0.0000

Data Index: 831846 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.7459. Min Act: -0.0000

Data Index: 874259 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.3641. Min Act: -0.0000

Data Index: 1203086 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.0706. Min Act: -0.0000

Data Index: 324726 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.1529. Min Act: -0.0000

Data Index: 1339397 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.2900. Min Act: -0.0000

Data Index: 937258 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.1136. Min Act: -0.0000

Data Index: 423773 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.0795. Min Act: -0.0000

Data Index: 672342 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 5.8485. Min Range: -5.8485

Max Act: 4.0257. Min Act: -0.0000

Data Index: 1143030 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 5.8485. Min Range: -5.8485

Max Act: 3.9198. Min Act: -0.0000

Data Index: 1357489 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 5.8485. Min Range: -5.8485

Max Act: 3.8365. Min Act: -0.0000

Data Index: 755028 (C4 (Web Text))

Max Activating Token Index: 48