Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3287 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.7234. Min Act: -0.0000

Data Index: 819861 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6334. Min Act: -0.0000

Data Index: 6966 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6054. Min Act: -0.0000

Data Index: 116882 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5952. Min Act: -0.0000

Data Index: 491776 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5821. Min Act: -0.0000

Data Index: 693634 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5255. Min Act: -0.0000

Data Index: 463653 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4908. Min Act: -0.0000

Data Index: 777191 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1249044 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5115. Min Act: -0.0000

Data Index: 658281 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5646. Min Act: -0.0000

Data Index: 950338 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1007918 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5175. Min Act: -0.0000

Data Index: 335716 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4752. Min Act: -0.0000

Data Index: 223027 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5052. Min Act: -0.0000

Data Index: 55307 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4829. Min Act: -0.0000

Data Index: 145947 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5202. Min Act: -0.0000

Data Index: 799013 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1136322 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4945. Min Act: -0.0000

Data Index: 280485 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1294048 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5301. Min Act: -0.0000

Data Index: 722644 (C4 (Web Text))

Max Activating Token Index: 780