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

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

Neuron 1627 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: 0.0406. Min Range: -0.0406

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1570791 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1636154 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0348. Min Act: -0.0002

Data Index: 312501 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1364809 (Python Code)

Max Activating Token Index: 234

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1458631 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0301. Min Act: -0.0002

Data Index: 684973 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1442930 (Python Code)

Max Activating Token Index: 105

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0281. Min Act: -0.0002

Data Index: 420378 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0268. Min Act: -0.0002

Data Index: 739703 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1360167 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0282. Min Act: -0.0002

Data Index: 992161 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0263. Min Act: -0.0002

Data Index: 657817 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0276. Min Act: -0.0002

Data Index: 819773 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1371547 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1560522 (Python Code)

Max Activating Token Index: 260

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1563681 (Python Code)

Max Activating Token Index: 681

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1550620 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0281. Min Act: -0.0002

Data Index: 745601 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1284460 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0243. Min Act: -0.0002

Data Index: 237191 (C4 (Web Text))

Max Activating Token Index: 96