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

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

Neuron 5113 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7407. Min Act: -0.0001

Data Index: 1551821 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7944. Min Act: -0.0001

Data Index: 576078 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7471. Min Act: -0.0000

Data Index: 133626 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7805. Min Act: -0.0000

Data Index: 163621 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1302773 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6936. Min Act: -0.0001

Data Index: 723980 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6860. Min Act: -0.0000

Data Index: 976657 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1289559 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1133765 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1255611 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6679. Min Act: -0.0000

Data Index: 144312 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1298509 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6637. Min Act: -0.0000

Data Index: 366868 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6807. Min Act: -0.0001

Data Index: 644049 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6563. Min Act: -0.0000

Data Index: 40838 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6266. Min Act: -0.0001

Data Index: 776594 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6444. Min Act: -0.0000

Data Index: 734717 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6832. Min Act: -0.0001

Data Index: 554754 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1261088 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6439. Min Act: -0.0000

Data Index: 396090 (C4 (Web Text))

Max Activating Token Index: 794