Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 758 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4832. Min Range: -2.4832

Max Act: 2.4347. Min Act: -0.0000

Data Index: 1357289 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 2.4832. Min Range: -2.4832

Max Act: 2.4832. Min Act: -0.0000

Data Index: 765809 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 2.4832. Min Range: -2.4832

Max Act: 2.0577. Min Act: -0.0000

Data Index: 1014696 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 2.4832. Min Range: -2.4832

Max Act: 2.1106. Min Act: -0.0000

Data Index: 1281884 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 2.4832. Min Range: -2.4832

Max Act: 2.0888. Min Act: -0.0000

Data Index: 994894 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.8646. Min Act: -0.0000

Data Index: 208021 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.9416. Min Act: -0.0000

Data Index: 309256 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.6748. Min Act: -0.0000

Data Index: 110448 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.8641. Min Act: -0.0000

Data Index: 716833 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.7377. Min Act: -0.0000

Data Index: 1230029 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.6907. Min Act: -0.0000

Data Index: 731521 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.7983. Min Act: -0.0000

Data Index: 75476 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1270119 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.5077. Min Act: -0.0000

Data Index: 75232 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1065466 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.4576. Min Act: -0.0000

Data Index: 844087 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.4527. Min Act: -0.0000

Data Index: 855376 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.5192. Min Act: -0.0000

Data Index: 841252 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.4788. Min Act: -0.0000

Data Index: 554384 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 2.4832. Min Range: -2.4832

Max Act: 1.4875. Min Act: -0.0000

Data Index: 1224078 (C4 (Web Text))

Max Activating Token Index: 413