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

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

Neuron 3220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5563. Min Range: -5.5563

Max Act: 5.5563. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 5.5563. Min Range: -5.5563

Max Act: 5.4716. Min Act: -0.0000

Data Index: 368457 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 5.5563. Min Range: -5.5563

Max Act: 5.2421. Min Act: -0.0000

Data Index: 1213295 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 5.5563. Min Range: -5.5563

Max Act: 5.4551. Min Act: -0.0000

Data Index: 1337091 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 5.5563. Min Range: -5.5563

Max Act: 5.3775. Min Act: -0.0000

Data Index: 374241 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 5.5563. Min Range: -5.5563

Max Act: 5.0361. Min Act: -0.0000

Data Index: 1183237 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.9064. Min Act: -0.0000

Data Index: 70704 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.9100. Min Act: -0.0000

Data Index: 1270098 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.7378. Min Act: -0.0000

Data Index: 33881 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.5274. Min Act: -0.0000

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.5371. Min Act: -0.0000

Data Index: 978761 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.6509. Min Act: -0.0000

Data Index: 1233880 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.7940. Min Act: -0.0000

Data Index: 287938 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.7922. Min Act: -0.0000

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.7036. Min Act: -0.0000

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.3129. Min Act: -0.0000

Data Index: 819689 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.1427. Min Act: -0.0000

Data Index: 303923 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.1077. Min Act: -0.0000

Data Index: 769469 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.4083. Min Act: -0.0000

Data Index: 1100773 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 5.5563. Min Range: -5.5563

Max Act: 4.2284. Min Act: -0.0000

Data Index: 271475 (C4 (Web Text))

Max Activating Token Index: 76