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

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

Neuron 734 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: 3.7013. Min Range: -3.7013

Max Act: 3.7013. Min Act: -0.1700

Data Index: 1114127 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.6398. Min Act: -0.1700

Data Index: 706893 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.6437. Min Act: -0.1700

Data Index: 344052 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.6138. Min Act: -0.1700

Data Index: 1150559 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5995. Min Act: -0.1700

Data Index: 817958 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5982. Min Act: -0.1700

Data Index: 366480 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5995. Min Act: -0.1700

Data Index: 485487 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5829. Min Act: -0.1700

Data Index: 795213 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5822. Min Act: -0.1700

Data Index: 309803 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5646. Min Act: -0.1699

Data Index: 1085956 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5698. Min Act: -0.1700

Data Index: 1358524 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5729. Min Act: -0.1700

Data Index: 666205 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5551. Min Act: -0.1696

Data Index: 878393 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5617. Min Act: -0.1700

Data Index: 501375 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5392. Min Act: -0.1700

Data Index: 1100460 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5372. Min Act: -0.1700

Data Index: 147288 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5448. Min Act: -0.1700

Data Index: 332439 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5426. Min Act: -0.1700

Data Index: 1262370 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5225. Min Act: -0.1700

Data Index: 239432 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 3.7013. Min Range: -3.7013

Max Act: 3.5177. Min Act: -0.1700

Data Index: 1119850 (C4 (Web Text))

Max Activating Token Index: 790