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

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

Neuron 2063 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2360. Min Act: -0.0000

Data Index: 925846 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2180. Min Act: -0.0000

Data Index: 926651 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1271040 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1914. Min Act: -0.0000

Data Index: 872078 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1903. Min Act: -0.0000

Data Index: 575147 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1904. Min Act: -0.0000

Data Index: 235314 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1270583 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1820. Min Act: -0.0000

Data Index: 935176 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1884. Min Act: -0.0000

Data Index: 908926 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1102743 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1802. Min Act: -0.0000

Data Index: 632365 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1053982 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1188152 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1779. Min Act: -0.0000

Data Index: 119290 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1873. Min Act: -0.0000

Data Index: 953087 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1227882 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1327094 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1954. Min Act: -0.0000

Data Index: 90079 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1764. Min Act: -0.0000

Data Index: 644205 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1054031 (C4 (Web Text))

Max Activating Token Index: 891