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

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

Neuron 2453 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: 1.2670. Min Range: -1.2670

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1096341 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.2670. Min Act: -0.0001

Data Index: 772290 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.0863. Min Act: -0.0001

Data Index: 1346638 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.1406. Min Act: -0.0001

Data Index: 181595 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.1434. Min Act: -0.0000

Data Index: 927486 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.1118. Min Act: -0.0001

Data Index: 408392 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.0642. Min Act: -0.0001

Data Index: 1346499 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1044215 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.0160. Min Act: -0.0000

Data Index: 733730 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.9887. Min Act: -0.0001

Data Index: 694799 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.9771. Min Act: -0.0000

Data Index: 232377 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.0216. Min Act: -0.0001

Data Index: 182860 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.9965. Min Act: -0.0001

Data Index: 293068 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 1.2670. Min Range: -1.2670

Max Act: 1.0126. Min Act: -0.0001

Data Index: 1208950 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.9709. Min Act: -0.0001

Data Index: 55545 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.9270. Min Act: -0.0000

Data Index: 111089 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8909. Min Act: -0.0001

Data Index: 971540 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8737. Min Act: -0.0001

Data Index: 754710 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.9007. Min Act: -0.0001

Data Index: 1239082 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.2670. Min Range: -1.2670

Max Act: 0.8775. Min Act: -0.0000

Data Index: 239166 (C4 (Web Text))

Max Activating Token Index: 881