Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 442 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.5682. Min Act: -0.1700

Data Index: 1214616 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.4742. Min Act: -0.1700

Data Index: 1116673 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.4429. Min Act: -0.1700

Data Index: 473977 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.4115. Min Act: -0.1700

Data Index: 1019409 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.4429. Min Act: -0.1700

Data Index: 1239279 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3801. Min Act: -0.1700

Data Index: 1254706 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.4115. Min Act: -0.1700

Data Index: 78374 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3801. Min Act: -0.1700

Data Index: 342093 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3801. Min Act: -0.1700

Data Index: 698553 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3488. Min Act: -0.1700

Data Index: 987376 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3801. Min Act: -0.1700

Data Index: 559169 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3801. Min Act: -0.1700

Data Index: 384411 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3174. Min Act: -0.1700

Data Index: 464944 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3488. Min Act: -0.1700

Data Index: 923595 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3174. Min Act: -0.1700

Data Index: 256616 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3488. Min Act: -0.1700

Data Index: 188681 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3488. Min Act: -0.1700

Data Index: 437766 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1136273 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3488. Min Act: -0.1700

Data Index: 912035 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3174. Min Act: -0.1700

Data Index: 497137 (C4 (Web Text))

Max Activating Token Index: 412