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

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

Neuron 3905 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.8280. Min Act: -0.0001

Data Index: 410397 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5740. Min Act: -0.0001

Data Index: 775110 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.6372. Min Act: -0.0001

Data Index: 1333286 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5617. Min Act: -0.0001

Data Index: 463694 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1688. Min Act: -0.0001

Data Index: 190928 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1005905 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5201. Min Act: -0.0000

Data Index: 492698 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.3591. Min Act: -0.0001

Data Index: 790160 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.3640. Min Act: -0.0001

Data Index: 479137 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0504. Min Act: -0.0000

Data Index: 471395 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1220. Min Act: -0.0001

Data Index: 104516 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0436. Min Act: -0.0001

Data Index: 947423 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1056. Min Act: -0.0000

Data Index: 133634 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 1.8280. Min Range: -1.8280

Max Act: 0.9780. Min Act: -0.0001

Data Index: 302141 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 1.8280. Min Range: -1.8280

Max Act: 0.9589. Min Act: -0.0001

Data Index: 974221 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1149. Min Act: -0.0001

Data Index: 254373 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0689. Min Act: -0.0001

Data Index: 1314599 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0451. Min Act: -0.0001

Data Index: 728512 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 1.8280. Min Range: -1.8280

Max Act: 0.9833. Min Act: -0.0001

Data Index: 674704 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0084. Min Act: -0.0001

Data Index: 1234247 (C4 (Web Text))

Max Activating Token Index: 344