Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3800 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.5581. Min Act: -0.0000

Data Index: 837568 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.6985. Min Act: -0.0000

Data Index: 576490 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.4053. Min Act: -0.0000

Data Index: 395219 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.4764. Min Act: -0.0000

Data Index: 394207 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.4786. Min Act: -0.0000

Data Index: 25275 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.0734. Min Act: -0.0000

Data Index: 1271587 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.1799. Min Act: -0.0000

Data Index: 246359 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 2.6985. Min Range: -2.6985

Max Act: 2.1568. Min Act: 0.0000

Data Index: 486344 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.9269. Min Act: -0.0000

Data Index: 712532 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1329436 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1202362 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8323. Min Act: -0.0000

Data Index: 1100629 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.9343. Min Act: -0.0000

Data Index: 349748 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.7631. Min Act: -0.0000

Data Index: 332846 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8248. Min Act: 0.0000

Data Index: 862372 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8053. Min Act: -0.0000

Data Index: 543257 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.7029. Min Act: -0.0000

Data Index: 697272 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.6981. Min Act: -0.0000

Data Index: 902288 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.8012. Min Act: -0.0000

Data Index: 376647 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 2.6985. Min Range: -2.6985

Max Act: 1.7702. Min Act: -0.0000

Data Index: 874961 (C4 (Web Text))

Max Activating Token Index: 934