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

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

Neuron 479 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2648. Min Range: -2.2648

Max Act: 2.0592. Min Act: -0.0000

Data Index: 1380645 (Python Code)

Max Activating Token Index: 806

Text #1

Max Range: 2.2648. Min Range: -2.2648

Max Act: 2.2648. Min Act: -0.0000

Data Index: 1366794 (Python Code)

Max Activating Token Index: 758

Text #2

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.9702. Min Act: -0.0000

Data Index: 176544 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.7135. Min Act: -0.0000

Data Index: 909932 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.6961. Min Act: -0.0000

Data Index: 91502 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.6109. Min Act: -0.0000

Data Index: 1460847 (Python Code)

Max Activating Token Index: 93

Text #6

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.6919. Min Act: -0.0000

Data Index: 1518693 (Python Code)

Max Activating Token Index: 908

Text #7

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.4404. Min Act: -0.0000

Data Index: 471946 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.5526. Min Act: -0.0000

Data Index: 1071811 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.5098. Min Act: -0.0000

Data Index: 349680 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1146667 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1383559 (Python Code)

Max Activating Token Index: 492

Text #12

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1362274 (Python Code)

Max Activating Token Index: 298

Text #13

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.3879. Min Act: -0.0000

Data Index: 737090 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.2873. Min Act: -0.0000

Data Index: 1351915 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.3702. Min Act: -0.0000

Data Index: 892881 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.2746. Min Act: -0.0000

Data Index: 315228 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.4041. Min Act: -0.0000

Data Index: 921983 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.3208. Min Act: -0.0000

Data Index: 205223 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 2.2648. Min Range: -2.2648

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1577829 (Python Code)

Max Activating Token Index: 723