Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 801 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.3080. Min Act: -0.0001

Data Index: 1193857 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.3182. Min Act: -0.0001

Data Index: 960890 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.2989. Min Act: -0.0001

Data Index: 745314 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.3352. Min Act: -0.0001

Data Index: 213394 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.2993. Min Act: -0.0001

Data Index: 420314 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1390. Min Act: -0.0001

Data Index: 709309 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.2759. Min Act: -0.0001

Data Index: 297654 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.2064. Min Act: -0.0001

Data Index: 896424 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1607. Min Act: -0.0001

Data Index: 140062 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1624. Min Act: -0.0001

Data Index: 574602 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.2543. Min Act: -0.0001

Data Index: 1138555 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.2037. Min Act: -0.0001

Data Index: 1208306 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1977. Min Act: -0.0001

Data Index: 1217639 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1856. Min Act: -0.0001

Data Index: 396753 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1814. Min Act: -0.0001

Data Index: 826385 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.2174. Min Act: -0.0001

Data Index: 349797 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.2158. Min Act: -0.0001

Data Index: 1549178 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1644. Min Act: -0.0001

Data Index: 850208 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.0777. Min Act: -0.0001

Data Index: 916861 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.3352. Min Range: -1.3352

Max Act: 1.1378. Min Act: -0.0001

Data Index: 1210228 (C4 (Web Text))

Max Activating Token Index: 131