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

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

Neuron 4373 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.7710. Min Act: -0.0000

Data Index: 1622143 (Python Code)

Max Activating Token Index: 716

Text #1

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.4713. Min Act: -0.0000

Data Index: 1406757 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3107. Min Act: -0.0000

Data Index: 1572895 (Python Code)

Max Activating Token Index: 178

Text #3

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1428592 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1369305 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2256. Min Act: -0.0000

Data Index: 1451681 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1545699 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1415088 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1380030 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1385619 (Python Code)

Max Activating Token Index: 568

Text #10

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3641. Min Act: -0.0000

Data Index: 1537185 (Python Code)

Max Activating Token Index: 893

Text #11

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1428877 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1491076 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2057. Min Act: -0.0000

Data Index: 1450972 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1625090 (Python Code)

Max Activating Token Index: 625

Text #15

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1650137 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2522. Min Act: -0.0000

Data Index: 1370485 (Python Code)

Max Activating Token Index: 681

Text #17

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1535847 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1574159 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 1.7710. Min Range: -1.7710

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1439532 (Python Code)

Max Activating Token Index: 634