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

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

Neuron 1366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.7303. Min Act: -0.0000

Data Index: 691203 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.7578. Min Act: -0.0000

Data Index: 705858 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.6777. Min Act: -0.0000

Data Index: 640784 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.6431. Min Act: -0.0000

Data Index: 971558 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1005683 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1174554 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.5344. Min Act: -0.0000

Data Index: 461182 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4868. Min Act: -0.0000

Data Index: 328158 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1179430 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4783. Min Act: -0.0000

Data Index: 784272 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1181239 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4955. Min Act: -0.0000

Data Index: 789107 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.5031. Min Act: -0.0000

Data Index: 18579 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1238709 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4809. Min Act: -0.0000

Data Index: 297305 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1596926 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1164291 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1304109 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4993. Min Act: -0.0000

Data Index: 200743 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.7578. Min Range: -0.7578

Max Act: 0.4749. Min Act: -0.0000

Data Index: 144461 (C4 (Web Text))

Max Activating Token Index: 72