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

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

Neuron 1625 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2439. Min Act: -0.0000

Data Index: 898270 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1111806 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2187. Min Act: -0.0000

Data Index: 813067 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1935. Min Act: -0.0000

Data Index: 912421 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.2000. Min Act: -0.0000

Data Index: 259730 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1994. Min Act: -0.0000

Data Index: 104018 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1933. Min Act: 0.0000

Data Index: 1208745 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1862. Min Act: -0.0000

Data Index: 856512 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1991. Min Act: -0.0000

Data Index: 269895 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1817. Min Act: -0.0000

Data Index: 707815 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1748. Min Act: -0.0000

Data Index: 580004 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1724. Min Act: -0.0000

Data Index: 614662 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1825. Min Act: -0.0000

Data Index: 812216 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1822. Min Act: -0.0000

Data Index: 698450 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1816. Min Act: -0.0000

Data Index: 629936 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1300805 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1305861 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1741. Min Act: -0.0000

Data Index: 146774 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1860. Min Act: -0.0000

Data Index: 244267 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.2439. Min Range: -0.2439

Max Act: 0.1811. Min Act: -0.0000

Data Index: 691645 (C4 (Web Text))

Max Activating Token Index: 938