Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1716 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0003

Data Index: 933966 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0299. Min Act: -0.0003

Data Index: 649533 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0281. Min Act: -0.0003

Data Index: 368009 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0287. Min Act: -0.0003

Data Index: 801501 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0291. Min Act: -0.0003

Data Index: 126464 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1341642 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0278. Min Act: -0.0003

Data Index: 264005 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1231883 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1055674 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0266. Min Act: -0.0003

Data Index: 710131 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1358579 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0271. Min Act: -0.0003

Data Index: 549213 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0275. Min Act: -0.0003

Data Index: 253865 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0281. Min Act: -0.0003

Data Index: 753087 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0271. Min Act: -0.0003

Data Index: 385629 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0251. Min Act: -0.0003

Data Index: 681238 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0284. Min Act: -0.0003

Data Index: 466305 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0275. Min Act: -0.0003

Data Index: 228842 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0251. Min Act: -0.0003

Data Index: 723197 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0284. Min Act: -0.0003

Data Index: 516807 (C4 (Web Text))

Max Activating Token Index: 139