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

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

Neuron 496 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: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0003

Data Index: 571328 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1197981 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0315. Min Act: -0.0003

Data Index: 147689 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1249801 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0265. Min Act: -0.0003

Data Index: 686840 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1251187 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0324. Min Act: -0.0003

Data Index: 723779 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1317362 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0285. Min Act: -0.0003

Data Index: 364206 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0280. Min Act: -0.0003

Data Index: 740303 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0267. Min Act: -0.0003

Data Index: 424574 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1051917 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0285. Min Act: -0.0003

Data Index: 377881 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0263. Min Act: -0.0003

Data Index: 145913 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0250. Min Act: -0.0003

Data Index: 487822 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1105070 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0241. Min Act: -0.0003

Data Index: 368328 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0273. Min Act: -0.0003

Data Index: 931110 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0242. Min Act: -0.0003

Data Index: 75293 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0249. Min Act: -0.0003

Data Index: 664988 (C4 (Web Text))

Max Activating Token Index: 174