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

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

Neuron 3228 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5830. Min Range: -5.5830

Max Act: 5.4676. Min Act: -0.0000

Data Index: 394166 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 5.5830. Min Range: -5.5830

Max Act: 5.5830. Min Act: -0.0000

Data Index: 1613632 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 5.5830. Min Range: -5.5830

Max Act: 5.4071. Min Act: -0.0000

Data Index: 1411802 (Python Code)

Max Activating Token Index: 219

Text #3

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.8104. Min Act: -0.0000

Data Index: 238242 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.9024. Min Act: -0.0000

Data Index: 1373212 (Python Code)

Max Activating Token Index: 168

Text #5

Max Range: 5.5830. Min Range: -5.5830

Max Act: 5.0112. Min Act: -0.0000

Data Index: 1332864 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.9450. Min Act: -0.0000

Data Index: 536691 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.3809. Min Act: -0.0000

Data Index: 1057772 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.6498. Min Act: -0.0000

Data Index: 1052524 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.2804. Min Act: -0.0000

Data Index: 412489 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 5.5830. Min Range: -5.5830

Max Act: 3.9386. Min Act: -0.0000

Data Index: 1239596 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.6479. Min Act: -0.0000

Data Index: 1032712 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.5115. Min Act: -0.0000

Data Index: 1028858 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.3738. Min Act: -0.0000

Data Index: 1294256 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.3814. Min Act: -0.0000

Data Index: 616047 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.3306. Min Act: -0.0000

Data Index: 13733 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.4794. Min Act: -0.0000

Data Index: 701649 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.4936. Min Act: -0.0000

Data Index: 335751 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.0720. Min Act: -0.0000

Data Index: 1124556 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 5.5830. Min Range: -5.5830

Max Act: 4.0611. Min Act: -0.0000

Data Index: 1139862 (C4 (Web Text))

Max Activating Token Index: 878