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

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

Neuron 5447 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2322. Min Range: -4.2322

Max Act: 4.2322. Min Act: -0.0000

Data Index: 400204 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 4.2322. Min Range: -4.2322

Max Act: 4.1355. Min Act: -0.0000

Data Index: 31102 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 4.2322. Min Range: -4.2322

Max Act: 4.1347. Min Act: -0.0000

Data Index: 210121 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.8446. Min Act: -0.0000

Data Index: 1186412 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.9694. Min Act: -0.0000

Data Index: 517499 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.3802. Min Act: -0.0000

Data Index: 663927 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.3541. Min Act: -0.0000

Data Index: 774254 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.5037. Min Act: -0.0000

Data Index: 635129 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.4554. Min Act: -0.0000

Data Index: 8075 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.2077. Min Act: -0.0000

Data Index: 126879 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.0544. Min Act: -0.0000

Data Index: 752656 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.1832. Min Act: -0.0000

Data Index: 979810 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.1016. Min Act: -0.0000

Data Index: 691982 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 4.2322. Min Range: -4.2322

Max Act: 2.9559. Min Act: -0.0000

Data Index: 310060 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 4.2322. Min Range: -4.2322

Max Act: 2.9078. Min Act: -0.0000

Data Index: 981702 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.0690. Min Act: -0.0000

Data Index: 125854 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.2071. Min Act: -0.0000

Data Index: 898384 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 4.2322. Min Range: -4.2322

Max Act: 2.9910. Min Act: -0.0000

Data Index: 1037786 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 4.2322. Min Range: -4.2322

Max Act: 3.0831. Min Act: -0.0000

Data Index: 627399 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 4.2322. Min Range: -4.2322

Max Act: 2.9088. Min Act: -0.0000

Data Index: 1338272 (C4 (Web Text))

Max Activating Token Index: 214