Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1642 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1031. Min Range: -1.1031

Max Act: 1.1031. Min Act: -0.0001

Data Index: 1097667 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9367. Min Act: -0.0001

Data Index: 351127 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8982. Min Act: -0.0001

Data Index: 737040 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8732. Min Act: -0.0001

Data Index: 981277 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8687. Min Act: -0.0001

Data Index: 588895 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8075. Min Act: -0.0001

Data Index: 643055 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8492. Min Act: -0.0001

Data Index: 570902 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7912. Min Act: -0.0001

Data Index: 335161 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7690. Min Act: -0.0001

Data Index: 132851 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7990. Min Act: -0.0001

Data Index: 109829 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7771. Min Act: -0.0001

Data Index: 537124 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8153. Min Act: -0.0001

Data Index: 91540 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7860. Min Act: -0.0001

Data Index: 143298 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7032. Min Act: -0.0001

Data Index: 659449 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7416. Min Act: -0.0001

Data Index: 297138 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.6854. Min Act: -0.0001

Data Index: 250002 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7108. Min Act: -0.0001

Data Index: 18043 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.6469. Min Act: -0.0001

Data Index: 445065 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.6848. Min Act: -0.0001

Data Index: 651773 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1170713 (C4 (Web Text))

Max Activating Token Index: 146