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

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

Neuron 1224 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.9341. Min Act: -0.0000

Data Index: 1233616 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.7118. Min Act: -0.0000

Data Index: 979185 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.6625. Min Act: -0.0000

Data Index: 641118 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.8338. Min Act: -0.0000

Data Index: 801298 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.5334. Min Act: -0.0000

Data Index: 68027 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.5241. Min Act: -0.0000

Data Index: 1011069 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.1476. Min Act: -0.0000

Data Index: 961346 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.1358. Min Act: -0.0000

Data Index: 997680 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.1315. Min Act: -0.0000

Data Index: 685273 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.0828. Min Act: -0.0000

Data Index: 914749 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.0165. Min Act: -0.0000

Data Index: 984130 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 4.9341. Min Range: -4.9341

Max Act: 3.9832. Min Act: -0.0000

Data Index: 910377 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 4.9341. Min Range: -4.9341

Max Act: 3.9173. Min Act: -0.0000

Data Index: 291483 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 4.9341. Min Range: -4.9341

Max Act: 4.0631. Min Act: -0.0000

Data Index: 221416 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 4.9341. Min Range: -4.9341

Max Act: 3.6571. Min Act: -0.0000

Data Index: 467950 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 4.9341. Min Range: -4.9341

Max Act: 3.8019. Min Act: -0.0000

Data Index: 261787 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 4.9341. Min Range: -4.9341

Max Act: 3.7799. Min Act: -0.0000

Data Index: 1156051 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 4.9341. Min Range: -4.9341

Max Act: 3.7817. Min Act: -0.0000

Data Index: 1340713 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 4.9341. Min Range: -4.9341

Max Act: 3.9173. Min Act: -0.0000

Data Index: 302386 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 4.9341. Min Range: -4.9341

Max Act: 3.7488. Min Act: -0.0000

Data Index: 69242 (C4 (Web Text))

Max Activating Token Index: 890