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

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

Neuron 1729 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2303. Min Act: -0.0001

Data Index: 604764 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1048522 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2268. Min Act: -0.0001

Data Index: 784458 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1480770 (Python Code)

Max Activating Token Index: 523

Text #4

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2093. Min Act: -0.0001

Data Index: 714871 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2166. Min Act: -0.0001

Data Index: 1237236 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2289. Min Act: -0.0001

Data Index: 1054806 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2168. Min Act: -0.0001

Data Index: 231510 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1954. Min Act: -0.0001

Data Index: 164292 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2139. Min Act: -0.0001

Data Index: 863428 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2375. Min Act: -0.0001

Data Index: 474441 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1155402 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1040552 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1999. Min Act: -0.0001

Data Index: 606740 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1197442 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1928. Min Act: -0.0001

Data Index: 866519 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2028. Min Act: -0.0001

Data Index: 660507 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1792. Min Act: -0.0001

Data Index: 1175409 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1069467 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1960. Min Act: -0.0001

Data Index: 964137 (C4 (Web Text))

Max Activating Token Index: 906