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

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

Neuron 1171 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: 0.2218. Min Range: -0.2218

Max Act: 0.2142. Min Act: -0.0002

Data Index: 1369247 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.2218. Min Act: -0.0002

Data Index: 1389488 (Python Code)

Max Activating Token Index: 368

Text #2

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.2042. Min Act: -0.0002

Data Index: 1651229 (Python Code)

Max Activating Token Index: 684

Text #3

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1500766 (Python Code)

Max Activating Token Index: 460

Text #4

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.2057. Min Act: -0.0002

Data Index: 1406836 (Python Code)

Max Activating Token Index: 878

Text #5

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.2019. Min Act: -0.0002

Data Index: 1450042 (Python Code)

Max Activating Token Index: 870

Text #6

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1994. Min Act: -0.0002

Data Index: 1451478 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1924. Min Act: -0.0002

Data Index: 1648058 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1926. Min Act: -0.0002

Data Index: 1385086 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1861. Min Act: -0.0002

Data Index: 1435557 (Python Code)

Max Activating Token Index: 394

Text #10

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1902. Min Act: -0.0002

Data Index: 1646868 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1867. Min Act: -0.0002

Data Index: 1503944 (Python Code)

Max Activating Token Index: 305

Text #12

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1913. Min Act: -0.0002

Data Index: 1486755 (Python Code)

Max Activating Token Index: 299

Text #13

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1858. Min Act: -0.0002

Data Index: 1644681 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1891. Min Act: -0.0002

Data Index: 1533599 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1885. Min Act: -0.0002

Data Index: 1640108 (Python Code)

Max Activating Token Index: 401

Text #16

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1794. Min Act: -0.0002

Data Index: 1518194 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1787. Min Act: -0.0002

Data Index: 1531306 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1769. Min Act: -0.0002

Data Index: 1517940 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 0.2218. Min Range: -0.2218

Max Act: 0.1910. Min Act: -0.0002

Data Index: 1576189 (Python Code)

Max Activating Token Index: 328