Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1827 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.5012. Min Act: -0.1700

Data Index: 881088 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.4074. Min Act: -0.1700

Data Index: 839493 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.2824. Min Act: -0.1700

Data Index: 1282334 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.2512. Min Act: -0.1700

Data Index: 568523 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.1887. Min Act: -0.1700

Data Index: 765459 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.2199. Min Act: -0.1700

Data Index: 390970 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.2199. Min Act: -0.1700

Data Index: 1036748 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.1887. Min Act: -0.1700

Data Index: 551575 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.2512. Min Act: -0.1700

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.1262. Min Act: -0.1700

Data Index: 1287147 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.1574. Min Act: -0.1700

Data Index: 85372 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.0949. Min Act: -0.1700

Data Index: 354329 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.1262. Min Act: -0.1700

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.0637. Min Act: -0.1700

Data Index: 360791 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.0012. Min Act: -0.1700

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.0949. Min Act: -0.1700

Data Index: 499085 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.1574. Min Act: -0.1700

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.0949. Min Act: -0.1700

Data Index: 1186798 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.1262. Min Act: -0.1700

Data Index: 764041 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 5.5012. Min Range: -5.5012

Max Act: 5.0324. Min Act: -0.1700

Data Index: 749935 (C4 (Web Text))

Max Activating Token Index: 525