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

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

Neuron 2656 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: 0.2799. Min Range: -0.2799

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1410437 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1461956 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1651082 (Python Code)

Max Activating Token Index: 411

Text #3

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1370488 (Python Code)

Max Activating Token Index: 531

Text #4

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1475106 (Python Code)

Max Activating Token Index: 660

Text #5

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1381109 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1578720 (Python Code)

Max Activating Token Index: 174

Text #7

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1472070 (Python Code)

Max Activating Token Index: 979

Text #8

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1499486 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1617354 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1618694 (Python Code)

Max Activating Token Index: 811

Text #11

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1465249 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1531564 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1380447 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1626321 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1415816 (Python Code)

Max Activating Token Index: 749

Text #16

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1542309 (Python Code)

Max Activating Token Index: 314

Text #17

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1452682 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1497674 (Python Code)

Max Activating Token Index: 553

Text #19

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1482638 (Python Code)

Max Activating Token Index: 648