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

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

Neuron 1171 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: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.0001

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8167. Min Act: -0.0001

Data Index: 957634 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7426. Min Act: -0.0001

Data Index: 525494 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7188. Min Act: -0.0001

Data Index: 618134 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7590. Min Act: -0.0001

Data Index: 233972 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7598. Min Act: -0.0001

Data Index: 1200806 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7165. Min Act: -0.0001

Data Index: 1027322 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7289. Min Act: -0.0001

Data Index: 897853 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7045. Min Act: -0.0001

Data Index: 313753 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6850. Min Act: -0.0001

Data Index: 1232426 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6664. Min Act: -0.0001

Data Index: 115633 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6900. Min Act: -0.0001

Data Index: 184877 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6449. Min Act: -0.0001

Data Index: 1160493 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6846. Min Act: -0.0001

Data Index: 1103717 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6454. Min Act: -0.0001

Data Index: 600144 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6935. Min Act: -0.0001

Data Index: 816806 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1466727 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6657. Min Act: -0.0001

Data Index: 44789 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6487. Min Act: -0.0001

Data Index: 273444 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6147. Min Act: -0.0001

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 881