Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1113 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.5502. Min Act: -0.0000

Data Index: 807826 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1162526 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.1193. Min Act: -0.0000

Data Index: 535765 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.0618. Min Act: -0.0000

Data Index: 220651 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1169728 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1142450 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9036. Min Act: -0.0000

Data Index: 529265 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1050712 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9260. Min Act: -0.0000

Data Index: 549540 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8595. Min Act: -0.0000

Data Index: 441033 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8922. Min Act: -0.0000

Data Index: 491782 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1104011 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8293. Min Act: -0.0000

Data Index: 184678 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1128038 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1291634 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8014. Min Act: -0.0000

Data Index: 221433 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8269. Min Act: -0.0000

Data Index: 798240 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7786. Min Act: -0.0000

Data Index: 211937 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7823. Min Act: -0.0000

Data Index: 728792 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.7582. Min Act: -0.0000

Data Index: 145187 (C4 (Web Text))

Max Activating Token Index: 940