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

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

Neuron 4155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.7784. Min Act: -0.0001

Data Index: 1060678 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.8419. Min Act: -0.0000

Data Index: 843071 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.7061. Min Act: -0.0000

Data Index: 25105 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.7695. Min Act: -0.0000

Data Index: 231398 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6789. Min Act: -0.0000

Data Index: 122458 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6517. Min Act: -0.0000

Data Index: 882298 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6297. Min Act: -0.0000

Data Index: 440988 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6216. Min Act: -0.0000

Data Index: 1269783 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6239. Min Act: -0.0000

Data Index: 1166461 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6191. Min Act: -0.0000

Data Index: 497034 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6062. Min Act: -0.0000

Data Index: 711762 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6096. Min Act: -0.0000

Data Index: 385273 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5366. Min Act: -0.0000

Data Index: 738671 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5840. Min Act: -0.0000

Data Index: 987973 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5670. Min Act: -0.0000

Data Index: 206464 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5944. Min Act: -0.0000

Data Index: 298044 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5384. Min Act: -0.0001

Data Index: 154670 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5604. Min Act: -0.0000

Data Index: 70264 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5097. Min Act: -0.0000

Data Index: 489997 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1263923 (C4 (Web Text))

Max Activating Token Index: 51