Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5103 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.4428. Min Act: -0.0000

Data Index: 161313 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.4424. Min Act: -0.0000

Data Index: 304731 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.2949. Min Act: -0.0000

Data Index: 481349 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1966. Min Act: -0.0000

Data Index: 455988 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.3194. Min Act: -0.0000

Data Index: 713162 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1797. Min Act: -0.0000

Data Index: 918336 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1293. Min Act: -0.0000

Data Index: 14317 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1158. Min Act: -0.0000

Data Index: 751744 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1683. Min Act: -0.0000

Data Index: 396134 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1249. Min Act: -0.0000

Data Index: 202276 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0917. Min Act: -0.0000

Data Index: 219579 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0841. Min Act: -0.0000

Data Index: 977838 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1359. Min Act: -0.0000

Data Index: 730967 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1034. Min Act: -0.0000

Data Index: 1247223 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0670. Min Act: -0.0000

Data Index: 359182 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9486. Min Act: -0.0000

Data Index: 940550 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9742. Min Act: -0.0000

Data Index: 161306 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9965. Min Act: -0.0000

Data Index: 504708 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1262163 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9615. Min Act: -0.0000

Data Index: 28369 (C4 (Web Text))

Max Activating Token Index: 842