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

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

Neuron 1050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.6397. Min Act: -0.0000

Data Index: 499661 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.3744. Min Act: -0.0000

Data Index: 468044 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.5251. Min Act: -0.0000

Data Index: 877224 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.3638. Min Act: -0.0000

Data Index: 883211 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.7929. Min Act: -0.0001

Data Index: 799577 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.3034. Min Act: -0.0001

Data Index: 918580 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.2915. Min Act: -0.0000

Data Index: 835661 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.2790. Min Act: -0.0001

Data Index: 569435 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.5455. Min Act: -0.0000

Data Index: 1343404 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.2049. Min Act: -0.0000

Data Index: 870640 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.2094. Min Act: -0.0000

Data Index: 939504 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.3651. Min Act: -0.0000

Data Index: 843509 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.3400. Min Act: -0.0000

Data Index: 156472 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.0557. Min Act: -0.0000

Data Index: 400321 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.4905. Min Act: -0.0000

Data Index: 967334 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.1754. Min Act: -0.0000

Data Index: 721695 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.4738. Min Act: -0.0000

Data Index: 1007150 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.6194. Min Act: -0.0000

Data Index: 224963 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.9944. Min Act: -0.0000

Data Index: 1015888 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.1193. Min Act: -0.0000

Data Index: 1266922 (C4 (Web Text))

Max Activating Token Index: 440