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

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

Neuron 2836 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1062149 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2667. Min Act: -0.0001

Data Index: 148877 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2399. Min Act: -0.0001

Data Index: 528994 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2260. Min Act: -0.0001

Data Index: 953739 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2362. Min Act: -0.0001

Data Index: 353129 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2048. Min Act: -0.0001

Data Index: 711180 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1259837 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2151. Min Act: -0.0001

Data Index: 657965 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2316. Min Act: -0.0001

Data Index: 618368 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2388. Min Act: -0.0001

Data Index: 406140 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2162. Min Act: -0.0001

Data Index: 74422 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2143. Min Act: -0.0001

Data Index: 269330 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1019850 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2053. Min Act: -0.0001

Data Index: 462855 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2164. Min Act: -0.0001

Data Index: 918708 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1997. Min Act: -0.0001

Data Index: 330222 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1346842 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2166. Min Act: -0.0001

Data Index: 956368 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1914. Min Act: -0.0001

Data Index: 930905 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2013. Min Act: -0.0001

Data Index: 572580 (C4 (Web Text))

Max Activating Token Index: 680