Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1356 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0694. Min Range: -3.0694

Max Act: 3.0694. Min Act: -0.1700

Data Index: 1101818 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 3.0694. Min Range: -3.0694

Max Act: 3.0221. Min Act: -0.1700

Data Index: 1171829 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9984. Min Act: -0.1700

Data Index: 35554 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9993. Min Act: -0.1700

Data Index: 1120257 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9805. Min Act: -0.1700

Data Index: 919443 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9796. Min Act: -0.1700

Data Index: 314746 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 3.0694. Min Range: -3.0694

Max Act: 3.0019. Min Act: -0.1700

Data Index: 101886 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9688. Min Act: -0.1700

Data Index: 523845 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9466. Min Act: -0.1700

Data Index: 797704 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9446. Min Act: -0.1700

Data Index: 220848 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9539. Min Act: -0.1700

Data Index: 760677 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9240. Min Act: -0.1700

Data Index: 38342 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9356. Min Act: -0.1700

Data Index: 477336 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9437. Min Act: -0.1700

Data Index: 847769 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9382. Min Act: -0.1700

Data Index: 656437 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9374. Min Act: -0.1700

Data Index: 1109651 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9160. Min Act: -0.1700

Data Index: 382927 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9588. Min Act: -0.1700

Data Index: 145917 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9248. Min Act: -0.1700

Data Index: 305891 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 3.0694. Min Range: -3.0694

Max Act: 2.9210. Min Act: -0.1700

Data Index: 129731 (C4 (Web Text))

Max Activating Token Index: 177