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

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

Neuron 5653 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: 1.3705. Min Range: -1.3705

Max Act: 1.3705. Min Act: -0.0000

Data Index: 285135 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1935. Min Act: -0.0000

Data Index: 414159 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.2486. Min Act: -0.0000

Data Index: 881777 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.2427. Min Act: -0.0000

Data Index: 887330 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1634. Min Act: -0.0000

Data Index: 817457 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1084884 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0930. Min Act: -0.0000

Data Index: 743765 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0917. Min Act: -0.0000

Data Index: 627696 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0950. Min Act: -0.0000

Data Index: 260999 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.1249. Min Act: -0.0000

Data Index: 681679 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0255. Min Act: -0.0000

Data Index: 648886 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9605. Min Act: -0.0000

Data Index: 704351 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9104. Min Act: -0.0000

Data Index: 567585 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9034. Min Act: -0.0000

Data Index: 798096 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1325240 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9559. Min Act: -0.0000

Data Index: 641788 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9623. Min Act: -0.0000

Data Index: 49724 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 1.3705. Min Range: -1.3705

Max Act: 1.0080. Min Act: -0.0000

Data Index: 996255 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.8865. Min Act: -0.0000

Data Index: 727285 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.3705. Min Range: -1.3705

Max Act: 0.9432. Min Act: -0.0000

Data Index: 142782 (C4 (Web Text))

Max Activating Token Index: 309