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

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

Neuron 4862 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0002

Data Index: 585179 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1563. Min Act: -0.0002

Data Index: 192799 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1262248 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1311. Min Act: -0.0002

Data Index: 1237710 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1277. Min Act: -0.0002

Data Index: 444840 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1271. Min Act: -0.0002

Data Index: 186312 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1202. Min Act: -0.0002

Data Index: 1297173 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1195. Min Act: -0.0002

Data Index: 1059485 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1086. Min Act: -0.0002

Data Index: 142556 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1127. Min Act: -0.0002

Data Index: 985835 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1167. Min Act: -0.0002

Data Index: 1144885 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1122102 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1200. Min Act: -0.0002

Data Index: 1167476 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1105. Min Act: -0.0002

Data Index: 460029 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1134. Min Act: -0.0002

Data Index: 508472 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1342087 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1145. Min Act: -0.0002

Data Index: 58587 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0985. Min Act: -0.0002

Data Index: 94554 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1057. Min Act: -0.0002

Data Index: 141730 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1072200 (C4 (Web Text))

Max Activating Token Index: 708