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

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

Neuron 1075 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: 0.2650. Min Range: -0.2650

Max Act: 0.2644. Min Act: -0.0000

Data Index: 459649 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2599. Min Act: -0.0000

Data Index: 762975 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2557. Min Act: -0.0000

Data Index: 199131 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2650. Min Act: -0.0000

Data Index: 943571 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2526. Min Act: -0.0000

Data Index: 421255 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2303. Min Act: -0.0000

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2368. Min Act: -0.0000

Data Index: 641557 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2570. Min Act: -0.0000

Data Index: 58591 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2235. Min Act: -0.0000

Data Index: 196105 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2166. Min Act: -0.0000

Data Index: 6871 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.2191. Min Act: -0.0000

Data Index: 921577 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1992. Min Act: -0.0000

Data Index: 327589 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1986. Min Act: -0.0000

Data Index: 709654 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1684. Min Act: -0.0000

Data Index: 76990 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1796. Min Act: -0.0000

Data Index: 536135 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1994. Min Act: -0.0000

Data Index: 804999 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1927. Min Act: -0.0000

Data Index: 159225 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1891. Min Act: -0.0000

Data Index: 209994 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1852. Min Act: -0.0000

Data Index: 834902 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.2650. Min Range: -0.2650

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1901 (C4 (Web Text))

Max Activating Token Index: 285