Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 254 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2496. Min Act: -0.0002

Data Index: 950431 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1972. Min Act: -0.0002

Data Index: 163168 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2036. Min Act: -0.0002

Data Index: 593184 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1963. Min Act: -0.0002

Data Index: 125049 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2050. Min Act: -0.0002

Data Index: 765102 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1997. Min Act: -0.0002

Data Index: 902500 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2001. Min Act: -0.0002

Data Index: 1318069 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1914. Min Act: -0.0002

Data Index: 813890 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1934. Min Act: -0.0002

Data Index: 518961 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2001. Min Act: -0.0002

Data Index: 943236 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1869. Min Act: -0.0002

Data Index: 198190 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1922. Min Act: -0.0002

Data Index: 1276383 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1932. Min Act: -0.0002

Data Index: 221542 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1827. Min Act: -0.0002

Data Index: 1090681 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1930. Min Act: -0.0002

Data Index: 729476 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1861. Min Act: -0.0002

Data Index: 1271728 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1859. Min Act: -0.0002

Data Index: 1039876 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1829. Min Act: -0.0002

Data Index: 39354 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1907. Min Act: -0.0002

Data Index: 368819 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1855. Min Act: -0.0002

Data Index: 1218461 (C4 (Web Text))

Max Activating Token Index: 807