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

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

Neuron 1503 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: 5.1401. Min Range: -5.1401

Max Act: 5.1401. Min Act: -0.1700

Data Index: 827392 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 5.1401. Min Range: -5.1401

Max Act: 5.1089. Min Act: -0.1700

Data Index: 230026 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 5.1401. Min Range: -5.1401

Max Act: 5.0464. Min Act: -0.1700

Data Index: 405429 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.9526. Min Act: -0.1700

Data Index: 939374 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.9526. Min Act: -0.1700

Data Index: 237794 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.9214. Min Act: -0.1700

Data Index: 806448 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.8901. Min Act: -0.1700

Data Index: 799452 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.8276. Min Act: -0.1700

Data Index: 550201 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.8589. Min Act: -0.1700

Data Index: 1243958 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.8276. Min Act: -0.1700

Data Index: 761965 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.8589. Min Act: -0.1700

Data Index: 731756 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.8276. Min Act: -0.1700

Data Index: 824680 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.7964. Min Act: -0.1700

Data Index: 161818 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.7964. Min Act: -0.1700

Data Index: 528623 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.7651. Min Act: -0.1700

Data Index: 804914 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.7651. Min Act: -0.1700

Data Index: 1262077 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.7339. Min Act: -0.1700

Data Index: 160520 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.7964. Min Act: -0.1700

Data Index: 819937 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.7339. Min Act: -0.1700

Data Index: 1033653 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 5.1401. Min Range: -5.1401

Max Act: 4.7026. Min Act: -0.1700

Data Index: 921893 (C4 (Web Text))

Max Activating Token Index: 239