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

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

Neuron 1046 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3618. Min Range: -1.3618

Max Act: 1.3618. Min Act: -0.0000

Data Index: 46100 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 1.3618. Min Range: -1.3618

Max Act: 1.2040. Min Act: -0.0000

Data Index: 140765 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 1.3618. Min Range: -1.3618

Max Act: 1.0176. Min Act: -0.0000

Data Index: 331141 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.3618. Min Range: -1.3618

Max Act: 1.0296. Min Act: -0.0000

Data Index: 973715 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.3618. Min Range: -1.3618

Max Act: 1.0075. Min Act: -0.0000

Data Index: 909302 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1622040 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.9394. Min Act: -0.0000

Data Index: 923736 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8824. Min Act: -0.0000

Data Index: 723286 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.9101. Min Act: -0.0000

Data Index: 674126 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.9043. Min Act: -0.0000

Data Index: 897926 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1133716 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1340776 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1376746 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8920. Min Act: -0.0000

Data Index: 153808 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8974. Min Act: -0.0000

Data Index: 996874 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8871. Min Act: -0.0000

Data Index: 633011 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8704. Min Act: -0.0000

Data Index: 463965 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8173. Min Act: -0.0000

Data Index: 502978 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8665. Min Act: -0.0000

Data Index: 969923 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 1.3618. Min Range: -1.3618

Max Act: 0.8626. Min Act: -0.0000

Data Index: 371025 (C4 (Web Text))

Max Activating Token Index: 192