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

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

Neuron 5434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1158011 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7715. Min Act: -0.0000

Data Index: 124802 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6960. Min Act: -0.0000

Data Index: 82527 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6644. Min Act: -0.0000

Data Index: 581054 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6436. Min Act: -0.0000

Data Index: 77096 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1274824 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6125. Min Act: -0.0000

Data Index: 291305 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6422. Min Act: -0.0000

Data Index: 207265 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6233. Min Act: -0.0000

Data Index: 182734 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6224. Min Act: -0.0000

Data Index: 43532 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1301162 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6307. Min Act: -0.0000

Data Index: 136070 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6253. Min Act: -0.0000

Data Index: 40727 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.5939. Min Act: -0.0000

Data Index: 512454 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6151. Min Act: -0.0000

Data Index: 387517 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6108. Min Act: -0.0000

Data Index: 886659 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1174001 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1174478 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1070576 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.5993. Min Act: -0.0000

Data Index: 29647 (C4 (Web Text))

Max Activating Token Index: 4