Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2530 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.8694. Min Act: -0.0001

Data Index: 1307257 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.2974. Min Act: -0.0001

Data Index: 533305 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1764. Min Act: -0.0001

Data Index: 573981 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.2254. Min Act: -0.0001

Data Index: 823160 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.3033. Min Act: -0.0001

Data Index: 351585 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1627. Min Act: -0.0001

Data Index: 62684 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1204. Min Act: -0.0001

Data Index: 860718 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.0211. Min Act: -0.0001

Data Index: 169384 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.0997. Min Act: -0.0001

Data Index: 7690 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.0574. Min Act: -0.0001

Data Index: 951739 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.9539. Min Act: -0.0001

Data Index: 1073760 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.0925. Min Act: -0.0001

Data Index: 929490 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.9991. Min Act: -0.0001

Data Index: 475796 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.9904. Min Act: -0.0001

Data Index: 1114592 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.9598. Min Act: -0.0001

Data Index: 949802 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.9840. Min Act: -0.0001

Data Index: 371475 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.9413. Min Act: -0.0001

Data Index: 595507 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.9630. Min Act: -0.0001

Data Index: 980664 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.8729. Min Act: -0.0001

Data Index: 1039368 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.8694. Min Range: -1.8694

Max Act: 0.9571. Min Act: -0.0001

Data Index: 1265316 (C4 (Web Text))

Max Activating Token Index: 802