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

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

Neuron 1690 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: 5.7846. Min Range: -5.7846

Max Act: 5.7846. Min Act: -0.1700

Data Index: 1012736 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.5033. Min Act: -0.1700

Data Index: 328441 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.5658. Min Act: -0.1700

Data Index: 1014062 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.5033. Min Act: -0.1700

Data Index: 316930 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3783. Min Act: -0.1700

Data Index: 418737 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.4096. Min Act: -0.1700

Data Index: 890875 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3783. Min Act: -0.1700

Data Index: 1308750 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3471. Min Act: -0.1700

Data Index: 611368 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3471. Min Act: -0.1700

Data Index: 193672 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.4408. Min Act: -0.1700

Data Index: 909628 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.4096. Min Act: -0.1700

Data Index: 395716 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3783. Min Act: -0.1700

Data Index: 440714 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3158. Min Act: -0.1700

Data Index: 199387 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3158. Min Act: -0.1700

Data Index: 879628 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3783. Min Act: -0.1700

Data Index: 176813 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3471. Min Act: -0.1700

Data Index: 1268855 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3783. Min Act: -0.1700

Data Index: 354681 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.3783. Min Act: -0.1700

Data Index: 448503 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.4096. Min Act: -0.1700

Data Index: 602205 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 5.7846. Min Range: -5.7846

Max Act: 5.2846. Min Act: -0.1700

Data Index: 583312 (C4 (Web Text))

Max Activating Token Index: 719