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

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

Neuron 3107 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.1683. Min Act: -0.0000

Data Index: 128928 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1293203 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.0741. Min Act: -0.0000

Data Index: 609071 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1057578 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.0246. Min Act: -0.0000

Data Index: 857588 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1037284 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9082. Min Act: 0.0000

Data Index: 1280690 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8943. Min Act: -0.0000

Data Index: 713540 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8377. Min Act: -0.0000

Data Index: 228904 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8861. Min Act: -0.0000

Data Index: 840663 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1176347 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8579. Min Act: -0.0000

Data Index: 525976 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1342401 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8469. Min Act: -0.0000

Data Index: 749044 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8252. Min Act: -0.0000

Data Index: 809120 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8659. Min Act: 0.0000

Data Index: 794523 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8142. Min Act: -0.0000

Data Index: 596706 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1034678 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8142. Min Act: -0.0000

Data Index: 622881 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8049. Min Act: -0.0000

Data Index: 373623 (C4 (Web Text))

Max Activating Token Index: 863