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

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

Neuron 1944 in Layer 3

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: 557636 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.7804. Min Act: -0.0001

Data Index: 833069 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.5198. Min Act: -0.0001

Data Index: 969129 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.3512. Min Act: -0.0001

Data Index: 870877 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2557. Min Act: -0.0001

Data Index: 1132735 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1983. Min Act: -0.0001

Data Index: 1197061 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2367. Min Act: -0.0001

Data Index: 230656 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2617. Min Act: -0.0001

Data Index: 193305 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1246. Min Act: -0.0001

Data Index: 161458 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1756. Min Act: -0.0001

Data Index: 1029950 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2161. Min Act: -0.0001

Data Index: 172089 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2096. Min Act: -0.0001

Data Index: 1073880 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1736. Min Act: -0.0001

Data Index: 449416 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.3545. Min Act: -0.0001

Data Index: 1139422 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2206. Min Act: -0.0001

Data Index: 1150173 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1423. Min Act: -0.0001

Data Index: 545757 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.2089. Min Act: -0.0001

Data Index: 284103 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0551. Min Act: -0.0001

Data Index: 360479 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.1616. Min Act: -0.0001

Data Index: 340448 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 1.8280. Min Range: -1.8280

Max Act: 1.0618. Min Act: -0.0001

Data Index: 655796 (C4 (Web Text))

Max Activating Token Index: 466