Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 424 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.6245. Min Act: -0.1700

Data Index: 754514 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.5932. Min Act: -0.1700

Data Index: 1230099 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.6245. Min Act: -0.1700

Data Index: 340080 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.5149. Min Act: -0.1700

Data Index: 263448 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.5149. Min Act: -0.1700

Data Index: 383434 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4836. Min Act: -0.1700

Data Index: 540897 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4836. Min Act: -0.1700

Data Index: 357681 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4992. Min Act: -0.1700

Data Index: 585515 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4836. Min Act: -0.1700

Data Index: 1239095 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4679. Min Act: -0.1700

Data Index: 1124256 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4992. Min Act: -0.1700

Data Index: 925048 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4836. Min Act: -0.1700

Data Index: 193643 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4836. Min Act: -0.1700

Data Index: 41382 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4679. Min Act: -0.1700

Data Index: 429345 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4365. Min Act: -0.1700

Data Index: 44662 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4365. Min Act: -0.1700

Data Index: 307642 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4365. Min Act: -0.1700

Data Index: 901322 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4365. Min Act: -0.1700

Data Index: 118869 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.4209. Min Act: -0.1700

Data Index: 982266 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 3.6245. Min Range: -3.6245

Max Act: 3.3738. Min Act: -0.1700

Data Index: 157622 (C4 (Web Text))

Max Activating Token Index: 905