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

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

Neuron 1608 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: 3.5555. Min Range: -3.5555

Max Act: 3.5555. Min Act: -0.1700

Data Index: 639586 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.5242. Min Act: -0.1700

Data Index: 384778 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4772. Min Act: -0.1700

Data Index: 348206 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4615. Min Act: -0.1700

Data Index: 1272728 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4615. Min Act: -0.1700

Data Index: 267708 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4301. Min Act: -0.1700

Data Index: 304856 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4772. Min Act: -0.1700

Data Index: 723175 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4615. Min Act: -0.1700

Data Index: 359914 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4772. Min Act: -0.1700

Data Index: 853984 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4615. Min Act: -0.1700

Data Index: 1308466 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4145. Min Act: -0.1700

Data Index: 306003 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4772. Min Act: -0.1700

Data Index: 1014221 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3988. Min Act: -0.1700

Data Index: 472929 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4928. Min Act: -0.1700

Data Index: 931432 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4145. Min Act: -0.1700

Data Index: 767866 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4145. Min Act: -0.1700

Data Index: 518771 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3988. Min Act: -0.1700

Data Index: 414118 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4772. Min Act: -0.1700

Data Index: 1285143 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4615. Min Act: -0.1700

Data Index: 732399 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3988. Min Act: -0.1700

Data Index: 524444 (C4 (Web Text))

Max Activating Token Index: 607