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

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

Neuron 3572 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0194. Min Range: -1.0194

Max Act: 1.0114. Min Act: -0.0000

Data Index: 794779 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.0194. Min Range: -1.0194

Max Act: 1.0194. Min Act: -0.0000

Data Index: 363664 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1068883 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.9008. Min Act: -0.0000

Data Index: 755634 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.9155. Min Act: -0.0000

Data Index: 645531 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1186884 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1207077 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8803. Min Act: -0.0000

Data Index: 459329 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8463. Min Act: -0.0000

Data Index: 529054 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.9202. Min Act: -0.0000

Data Index: 339037 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1293183 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8283. Min Act: -0.0000

Data Index: 781233 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1045446 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7687. Min Act: -0.0000

Data Index: 344148 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.8099. Min Act: -0.0000

Data Index: 185418 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7148. Min Act: -0.0000

Data Index: 242147 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.7286. Min Act: -0.0000

Data Index: 431919 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6965. Min Act: -0.0000

Data Index: 210670 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1205544 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.0194. Min Range: -1.0194

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1252402 (C4 (Web Text))

Max Activating Token Index: 265