Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2015 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0249. Min Act: -0.0005

Data Index: 1176596 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0245. Min Act: -0.0006

Data Index: 361581 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0224. Min Act: -0.0005

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0219. Min Act: -0.0005

Data Index: 343177 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0216. Min Act: -0.0005

Data Index: 1152946 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0211. Min Act: -0.0005

Data Index: 1234939 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0218. Min Act: -0.0006

Data Index: 895596 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0197. Min Act: -0.0006

Data Index: 167080 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0206. Min Act: -0.0006

Data Index: 231743 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0193. Min Act: -0.0006

Data Index: 398854 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0198. Min Act: -0.0005

Data Index: 1191435 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0192. Min Act: -0.0006

Data Index: 278107 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1329333 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0195. Min Act: -0.0005

Data Index: 759787 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0191. Min Act: -0.0005

Data Index: 450874 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0195. Min Act: -0.0005

Data Index: 740558 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0195. Min Act: -0.0005

Data Index: 342168 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0190. Min Act: -0.0005

Data Index: 280831 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0208. Min Act: -0.0006

Data Index: 887715 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0193. Min Act: -0.0006

Data Index: 645391 (C4 (Web Text))

Max Activating Token Index: 265