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

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

Neuron 3013 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: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0003

Data Index: 970686 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0320. Min Act: -0.0002

Data Index: 632305 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0267. Min Act: -0.0003

Data Index: 121493 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1356131 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0298. Min Act: -0.0003

Data Index: 565109 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0297. Min Act: -0.0003

Data Index: 843645 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0287. Min Act: -0.0003

Data Index: 533719 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1170697 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0288. Min Act: -0.0003

Data Index: 871072 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0285. Min Act: -0.0003

Data Index: 724568 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1281029 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0277. Min Act: -0.0003

Data Index: 517668 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0281. Min Act: -0.0003

Data Index: 258338 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0283. Min Act: -0.0003

Data Index: 791324 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0283. Min Act: -0.0003

Data Index: 327442 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0283. Min Act: -0.0003

Data Index: 469964 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1180516 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0266. Min Act: -0.0003

Data Index: 705167 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1081673 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1349132 (C4 (Web Text))

Max Activating Token Index: 109