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

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

Neuron 1851 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: 1.1793. Min Range: -1.1793

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1142622 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1279203 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 1.1793. Min Range: -1.1793

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1069684 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8993. Min Act: -0.0000

Data Index: 970188 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.9239. Min Act: -0.0000

Data Index: 273124 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.9131. Min Act: -0.0000

Data Index: 34093 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.9014. Min Act: -0.0000

Data Index: 747479 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8458. Min Act: -0.0000

Data Index: 908290 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1215821 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8825. Min Act: -0.0000

Data Index: 465173 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1350306 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8607. Min Act: -0.0000

Data Index: 979729 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8749. Min Act: -0.0000

Data Index: 876859 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7252. Min Act: -0.0000

Data Index: 482538 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7495. Min Act: -0.0000

Data Index: 548791 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7147. Min Act: -0.0000

Data Index: 291589 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1024489 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7123. Min Act: -0.0000

Data Index: 484192 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.6641. Min Act: -0.0000

Data Index: 789162 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7085. Min Act: -0.0000

Data Index: 662918 (C4 (Web Text))

Max Activating Token Index: 901