Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2892 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6513. Min Act: -0.0000

Data Index: 47013 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6278. Min Act: -0.0001

Data Index: 1077320 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6694. Min Act: -0.0000

Data Index: 30457 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6019. Min Act: -0.0001

Data Index: 1304066 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6379. Min Act: -0.0000

Data Index: 781514 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6022. Min Act: -0.0001

Data Index: 164406 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6604. Min Act: -0.0000

Data Index: 876502 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6386. Min Act: -0.0001

Data Index: 279082 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1333169 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.6063. Min Act: -0.0000

Data Index: 387043 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5752. Min Act: -0.0000

Data Index: 866405 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1123656 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5574. Min Act: -0.0001

Data Index: 606627 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5853. Min Act: -0.0001

Data Index: 696797 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5779. Min Act: -0.0000

Data Index: 927428 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5341. Min Act: -0.0001

Data Index: 101359 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5447. Min Act: -0.0000

Data Index: 524431 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5474. Min Act: -0.0000

Data Index: 945964 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5555. Min Act: -0.0000

Data Index: 603568 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.6694. Min Range: -0.6694

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1080372 (C4 (Web Text))

Max Activating Token Index: 737