Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4871 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3716. Min Act: -0.0000

Data Index: 723610 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2869. Min Act: -0.0000

Data Index: 146448 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2175. Min Act: -0.0000

Data Index: 641134 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2055. Min Act: -0.0000

Data Index: 7734 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1603562 (Python Code)

Max Activating Token Index: 714

Text #5

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1027907 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1042503 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1769. Min Act: -0.0000

Data Index: 83058 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1873. Min Act: -0.0000

Data Index: 382986 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1082217 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1640. Min Act: -0.0000

Data Index: 458992 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1962. Min Act: -0.0000

Data Index: 294095 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1796. Min Act: -0.0000

Data Index: 716444 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1675. Min Act: -0.0000

Data Index: 465805 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1788. Min Act: -0.0000

Data Index: 193783 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1728. Min Act: -0.0000

Data Index: 984753 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1766. Min Act: -0.0000

Data Index: 925532 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1721. Min Act: -0.0000

Data Index: 334330 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1645. Min Act: -0.0000

Data Index: 987442 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.1759. Min Act: -0.0000

Data Index: 883594 (C4 (Web Text))

Max Activating Token Index: 892