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

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

Neuron 3822 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0914. Min Act: -0.0002

Data Index: 813936 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0906. Min Act: -0.0001

Data Index: 746491 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1345505 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0899. Min Act: -0.0002

Data Index: 909167 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1334402 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0866. Min Act: -0.0002

Data Index: 309541 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0907. Min Act: -0.0002

Data Index: 84886 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0857. Min Act: -0.0001

Data Index: 830902 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0826. Min Act: -0.0001

Data Index: 320109 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0854. Min Act: -0.0002

Data Index: 667306 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1350259 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0834. Min Act: -0.0002

Data Index: 724946 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0834. Min Act: -0.0002

Data Index: 250198 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0841. Min Act: -0.0002

Data Index: 180514 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0800. Min Act: -0.0002

Data Index: 572670 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0777. Min Act: -0.0001

Data Index: 482536 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0897. Min Act: -0.0002

Data Index: 433020 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0851. Min Act: -0.0001

Data Index: 333050 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0783. Min Act: -0.0001

Data Index: 888860 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0811. Min Act: -0.0001

Data Index: 701095 (C4 (Web Text))

Max Activating Token Index: 614