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

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

Neuron 3589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.8158. Min Act: -0.0001

Data Index: 373091 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6266. Min Act: -0.0000

Data Index: 218479 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6059. Min Act: -0.0001

Data Index: 829833 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5251. Min Act: -0.0000

Data Index: 983546 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5577. Min Act: -0.0000

Data Index: 561280 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5386. Min Act: -0.0001

Data Index: 1106177 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5422. Min Act: -0.0001

Data Index: 760572 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5219. Min Act: -0.0001

Data Index: 421980 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5375. Min Act: -0.0001

Data Index: 120895 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5617. Min Act: -0.0001

Data Index: 396269 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5243. Min Act: -0.0001

Data Index: 397958 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5014. Min Act: -0.0000

Data Index: 81445 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5121. Min Act: -0.0000

Data Index: 211695 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5014. Min Act: -0.0000

Data Index: 176581 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5367. Min Act: -0.0001

Data Index: 406728 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5019. Min Act: -0.0001

Data Index: 633655 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.4970. Min Act: -0.0000

Data Index: 943400 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.4960. Min Act: -0.0001

Data Index: 304871 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.4800. Min Act: -0.0001

Data Index: 780934 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.4746. Min Act: -0.0000

Data Index: 460860 (C4 (Web Text))

Max Activating Token Index: 293