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

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

Neuron 478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.9002. Min Act: -0.0000

Data Index: 1208839 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.8544. Min Act: -0.0000

Data Index: 389690 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.8312. Min Act: -0.0000

Data Index: 1341262 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.7872. Min Act: -0.0000

Data Index: 1239246 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.7672. Min Act: -0.0000

Data Index: 15021 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.8530. Min Act: -0.0000

Data Index: 208461 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.8898. Min Act: -0.0000

Data Index: 924085 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5253. Min Act: -0.0000

Data Index: 624634 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5903. Min Act: -0.0000

Data Index: 960846 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5946. Min Act: -0.0000

Data Index: 1180186 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5486. Min Act: -0.0000

Data Index: 828886 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5297. Min Act: -0.0000

Data Index: 1032278 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5829. Min Act: -0.0000

Data Index: 772552 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5512. Min Act: -0.0000

Data Index: 1350300 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5357. Min Act: -0.0000

Data Index: 456501 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5292. Min Act: -0.0000

Data Index: 414862 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.4967. Min Act: -0.0000

Data Index: 393161 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.6193. Min Act: -0.0000

Data Index: 1344893 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.5916. Min Act: -0.0000

Data Index: 329642 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 1.9002. Min Range: -1.9002

Max Act: 1.4518. Min Act: -0.0000

Data Index: 689805 (C4 (Web Text))

Max Activating Token Index: 534