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

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

Neuron 4307 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1213871 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0895. Min Act: -0.0001

Data Index: 980817 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0934. Min Act: -0.0001

Data Index: 282700 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1337555 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1181482 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0769. Min Act: -0.0001

Data Index: 639612 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0909. Min Act: -0.0001

Data Index: 356267 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0820. Min Act: -0.0001

Data Index: 151660 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1218498 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0851. Min Act: -0.0001

Data Index: 363009 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0827. Min Act: -0.0001

Data Index: 883712 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0887. Min Act: -0.0001

Data Index: 679455 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1342839 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0988. Min Act: -0.0001

Data Index: 106667 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0780. Min Act: -0.0001

Data Index: 699234 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1232557 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0780. Min Act: -0.0001

Data Index: 547763 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1117377 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0745. Min Act: -0.0001

Data Index: 416998 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0835. Min Act: -0.0001

Data Index: 698678 (C4 (Web Text))

Max Activating Token Index: 469