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

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

Neuron 3770 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: 0.4810. Min Range: -0.4810

Max Act: 0.4810. Min Act: -0.0000

Data Index: 440214 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2758. Min Act: -0.0000

Data Index: 311739 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2979. Min Act: -0.0000

Data Index: 851012 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1050219 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2781. Min Act: -0.0000

Data Index: 233448 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2860. Min Act: -0.0000

Data Index: 17807 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2430. Min Act: -0.0000

Data Index: 528900 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2545. Min Act: -0.0000

Data Index: 31780 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2405. Min Act: -0.0000

Data Index: 670651 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1134533 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1097300 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2177. Min Act: -0.0000

Data Index: 128062 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2309. Min Act: -0.0000

Data Index: 766705 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2222. Min Act: -0.0000

Data Index: 178171 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2169. Min Act: -0.0000

Data Index: 765467 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2219. Min Act: -0.0000

Data Index: 254204 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2283. Min Act: -0.0000

Data Index: 407831 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2194. Min Act: -0.0000

Data Index: 516332 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2167. Min Act: -0.0000

Data Index: 675797 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.4810. Min Range: -0.4810

Max Act: 0.2151. Min Act: -0.0000

Data Index: 646376 (C4 (Web Text))

Max Activating Token Index: 830