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

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

Neuron 5339 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0805. Min Range: -7.0805

Max Act: 7.0805. Min Act: -0.0000

Data Index: 788193 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 7.0805. Min Range: -7.0805

Max Act: 5.7071. Min Act: -0.0000

Data Index: 523651 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 7.0805. Min Range: -7.0805

Max Act: 5.6913. Min Act: -0.0000

Data Index: 1306996 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 7.0805. Min Range: -7.0805

Max Act: 6.0689. Min Act: -0.0000

Data Index: 97933 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 7.0805. Min Range: -7.0805

Max Act: 5.4539. Min Act: -0.0000

Data Index: 34067 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 7.0805. Min Range: -7.0805

Max Act: 5.3624. Min Act: -0.0000

Data Index: 332392 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.8973. Min Act: -0.0000

Data Index: 1300008 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.4479. Min Act: -0.0000

Data Index: 125080 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.8796. Min Act: -0.0000

Data Index: 273414 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.7530. Min Act: -0.0000

Data Index: 250384 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.6389. Min Act: -0.0000

Data Index: 42891 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.5939. Min Act: -0.0000

Data Index: 441117 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.5616. Min Act: -0.0000

Data Index: 569618 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.5712. Min Act: -0.0000

Data Index: 952096 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.3741. Min Act: -0.0000

Data Index: 1357609 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.3387. Min Act: -0.0000

Data Index: 319964 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.4934. Min Act: -0.0000

Data Index: 1063756 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.4746. Min Act: -0.0000

Data Index: 192052 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.4744. Min Act: -0.0000

Data Index: 854402 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 7.0805. Min Range: -7.0805

Max Act: 4.3964. Min Act: -0.0000

Data Index: 1338048 (C4 (Web Text))

Max Activating Token Index: 787