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

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

Neuron 415 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.3022. Min Act: -0.0001

Data Index: 411905 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2654. Min Act: -0.0001

Data Index: 1039370 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2530. Min Act: -0.0001

Data Index: 557887 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2544. Min Act: -0.0001

Data Index: 70122 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2378. Min Act: -0.0000

Data Index: 680733 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2285. Min Act: -0.0001

Data Index: 1030470 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2302. Min Act: -0.0001

Data Index: 1194399 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1198770 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2229. Min Act: -0.0001

Data Index: 288020 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1042345 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2042. Min Act: -0.0001

Data Index: 310825 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2114. Min Act: -0.0001

Data Index: 840802 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2102. Min Act: -0.0001

Data Index: 3352 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2098. Min Act: -0.0001

Data Index: 460996 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2009. Min Act: -0.0000

Data Index: 817980 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2077. Min Act: -0.0001

Data Index: 288794 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2000. Min Act: -0.0001

Data Index: 971424 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2076. Min Act: -0.0001

Data Index: 277702 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2131. Min Act: -0.0001

Data Index: 648213 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.1993. Min Act: -0.0001

Data Index: 1350000 (C4 (Web Text))

Max Activating Token Index: 192