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

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

Neuron 3379 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: 5.9545. Min Range: -5.9545

Max Act: 5.9545. Min Act: -0.0000

Data Index: 623953 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 5.9545. Min Range: -5.9545

Max Act: 5.3694. Min Act: -0.0000

Data Index: 297951 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.8153. Min Act: -0.0000

Data Index: 540860 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 5.9545. Min Range: -5.9545

Max Act: 5.0800. Min Act: -0.0000

Data Index: 1284 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.8543. Min Act: -0.0000

Data Index: 1311685 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 5.9545. Min Range: -5.9545

Max Act: 5.1696. Min Act: -0.0000

Data Index: 230349 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.6709. Min Act: -0.0000

Data Index: 636718 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.6573. Min Act: -0.0000

Data Index: 407663 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.4569. Min Act: -0.0000

Data Index: 326733 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.5951. Min Act: -0.0000

Data Index: 692325 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.7975. Min Act: -0.0000

Data Index: 980078 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.1837. Min Act: -0.0000

Data Index: 360914 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 5.9545. Min Range: -5.9545

Max Act: 4.0719. Min Act: -0.0000

Data Index: 640397 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 5.9545. Min Range: -5.9545

Max Act: 3.6357. Min Act: -0.0000

Data Index: 1248123 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 5.9545. Min Range: -5.9545

Max Act: 3.4762. Min Act: -0.0000

Data Index: 782168 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 5.9545. Min Range: -5.9545

Max Act: 3.6393. Min Act: -0.0000

Data Index: 369558 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 5.9545. Min Range: -5.9545

Max Act: 3.6289. Min Act: -0.0000

Data Index: 1219513 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 5.9545. Min Range: -5.9545

Max Act: 3.2647. Min Act: -0.0000

Data Index: 767093 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 5.9545. Min Range: -5.9545

Max Act: 3.4871. Min Act: -0.0000

Data Index: 678333 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 5.9545. Min Range: -5.9545

Max Act: 3.1022. Min Act: -0.0000

Data Index: 1136870 (C4 (Web Text))

Max Activating Token Index: 767