Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 515 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1216655 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.5355. Min Act: -0.0000

Data Index: 121568 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4929. Min Act: -0.0000

Data Index: 988158 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4915. Min Act: -0.0000

Data Index: 550924 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4682. Min Act: -0.0000

Data Index: 725428 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4610. Min Act: -0.0001

Data Index: 795118 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4268. Min Act: -0.0000

Data Index: 38967 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4297. Min Act: -0.0001

Data Index: 1278719 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4169. Min Act: -0.0000

Data Index: 199431 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4143. Min Act: -0.0001

Data Index: 1089453 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3946. Min Act: -0.0000

Data Index: 732578 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4023. Min Act: -0.0000

Data Index: 559528 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.4048. Min Act: 0.0000

Data Index: 314643 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3828. Min Act: -0.0000

Data Index: 471886 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3789. Min Act: -0.0001

Data Index: 708675 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3926. Min Act: -0.0001

Data Index: 34642 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1318566 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3886. Min Act: -0.0000

Data Index: 324786 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3702. Min Act: -0.0000

Data Index: 66767 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.5454. Min Range: -0.5454

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1254622 (C4 (Web Text))

Max Activating Token Index: 966