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

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

Neuron 4051 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1019533 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0397. Min Act: -0.0002

Data Index: 21543 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0356. Min Act: -0.0002

Data Index: 249809 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0348. Min Act: -0.0002

Data Index: 497664 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0327. Min Act: -0.0003

Data Index: 38663 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0326. Min Act: -0.0002

Data Index: 441858 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0313. Min Act: -0.0002

Data Index: 580129 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1612757 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0292. Min Act: -0.0002

Data Index: 666156 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1618217 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1629275 (Python Code)

Max Activating Token Index: 600

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1481640 (Python Code)

Max Activating Token Index: 841

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1561546 (Python Code)

Max Activating Token Index: 612

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1422270 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0238. Min Act: -0.0002

Data Index: 420654 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1360673 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1499766 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1206988 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1483266 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1386908 (Python Code)

Max Activating Token Index: 244