Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1994 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0003

Data Index: 131663 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0220. Min Act: -0.0002

Data Index: 850113 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1000788 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1163354 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1053713 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1272789 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0204. Min Act: -0.0003

Data Index: 850573 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1314526 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0200. Min Act: -0.0003

Data Index: 527506 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1143864 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1019137 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0197. Min Act: -0.0003

Data Index: 705210 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0199. Min Act: -0.0003

Data Index: 947644 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0193. Min Act: -0.0003

Data Index: 128333 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0192. Min Act: -0.0003

Data Index: 927460 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0187. Min Act: -0.0003

Data Index: 939542 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0191. Min Act: -0.0002

Data Index: 826529 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0190. Min Act: -0.0003

Data Index: 930423 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0193. Min Act: -0.0003

Data Index: 869928 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0184. Min Act: -0.0003

Data Index: 176343 (C4 (Web Text))

Max Activating Token Index: 218