Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1750 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1338. Min Act: -0.0002

Data Index: 715087 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1215. Min Act: -0.0002

Data Index: 356569 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1321. Min Act: -0.0002

Data Index: 1446449 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1257. Min Act: -0.0002

Data Index: 880970 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1337. Min Act: -0.0002

Data Index: 1156890 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1090. Min Act: -0.0002

Data Index: 808801 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1127. Min Act: -0.0002

Data Index: 327860 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1127. Min Act: -0.0002

Data Index: 817197 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1026138 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1244888 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1027. Min Act: -0.0001

Data Index: 106875 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1041. Min Act: -0.0002

Data Index: 807124 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1029. Min Act: -0.0002

Data Index: 833554 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1079. Min Act: -0.0002

Data Index: 160112 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1043. Min Act: -0.0002

Data Index: 1350193 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1065. Min Act: -0.0002

Data Index: 326641 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1029. Min Act: -0.0002

Data Index: 664425 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0898. Min Act: -0.0002

Data Index: 915020 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1067. Min Act: -0.0001

Data Index: 100589 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0982. Min Act: -0.0002

Data Index: 861559 (C4 (Web Text))

Max Activating Token Index: 415