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

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

Neuron 1275 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.6111. Min Act: -0.1700

Data Index: 267814 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.6424. Min Act: -0.1700

Data Index: 704523 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.5486. Min Act: -0.1700

Data Index: 86183 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.5799. Min Act: -0.1700

Data Index: 1255144 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.5486. Min Act: -0.1700

Data Index: 15775 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4861. Min Act: -0.1700

Data Index: 150301 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4549. Min Act: -0.1700

Data Index: 528773 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4549. Min Act: -0.1700

Data Index: 196434 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4861. Min Act: -0.1700

Data Index: 951651 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4861. Min Act: -0.1700

Data Index: 774285 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4236. Min Act: -0.1700

Data Index: 527192 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4236. Min Act: -0.1700

Data Index: 595576 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4549. Min Act: -0.1700

Data Index: 133976 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4236. Min Act: -0.1700

Data Index: 1050219 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.4236. Min Act: -0.1700

Data Index: 913665 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.3611. Min Act: -0.1700

Data Index: 652573 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.3924. Min Act: -0.1700

Data Index: 304525 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.3924. Min Act: -0.1700

Data Index: 876854 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.3924. Min Act: -0.1700

Data Index: 490267 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 5.6424. Min Range: -5.6424

Max Act: 5.3299. Min Act: -0.1700

Data Index: 512127 (C4 (Web Text))

Max Activating Token Index: 616