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

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

Neuron 231 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: 1.0505. Min Range: -1.0505

Max Act: 1.0505. Min Act: -0.0000

Data Index: 963543 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9627. Min Act: -0.0001

Data Index: 247051 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 1.0505. Min Range: -1.0505

Max Act: 1.0070. Min Act: -0.0001

Data Index: 139926 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1508510 (Python Code)

Max Activating Token Index: 634

Text #4

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.9000. Min Act: -0.0001

Data Index: 1029639 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8922. Min Act: -0.0001

Data Index: 42009 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8874. Min Act: -0.0001

Data Index: 1492338 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8538. Min Act: -0.0001

Data Index: 1096495 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8746. Min Act: -0.0001

Data Index: 682496 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8851. Min Act: -0.0001

Data Index: 445888 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8501. Min Act: -0.0001

Data Index: 1501014 (Python Code)

Max Activating Token Index: 913

Text #11

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8940. Min Act: -0.0000

Data Index: 411744 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8411. Min Act: -0.0001

Data Index: 1287613 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8684. Min Act: -0.0001

Data Index: 920126 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.7965. Min Act: -0.0001

Data Index: 1016912 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8122. Min Act: -0.0001

Data Index: 741340 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8642. Min Act: -0.0001

Data Index: 873176 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1320453 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8241. Min Act: -0.0001

Data Index: 205195 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8422. Min Act: -0.0001

Data Index: 1536946 (Python Code)

Max Activating Token Index: 585