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

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

Neuron 1540 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: 4.2971. Min Range: -4.2971

Max Act: 4.2971. Min Act: -0.1700

Data Index: 218722 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 4.2971. Min Range: -4.2971

Max Act: 4.0626. Min Act: -0.1700

Data Index: 59609 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 4.2971. Min Range: -4.2971

Max Act: 4.0783. Min Act: -0.1700

Data Index: 634517 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.9845. Min Act: -0.1700

Data Index: 94994 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.9532. Min Act: -0.1700

Data Index: 1324709 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.9688. Min Act: -0.1700

Data Index: 2697 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.9219. Min Act: -0.1700

Data Index: 12030 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.9063. Min Act: -0.1700

Data Index: 533664 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8750. Min Act: -0.1700

Data Index: 636248 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8750. Min Act: -0.1700

Data Index: 575369 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8281. Min Act: -0.1700

Data Index: 425384 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8594. Min Act: -0.1700

Data Index: 464966 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8437. Min Act: -0.1700

Data Index: 64125 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8125. Min Act: -0.1700

Data Index: 172060 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8437. Min Act: -0.1700

Data Index: 869162 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8437. Min Act: -0.1700

Data Index: 1094096 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8281. Min Act: -0.1700

Data Index: 848953 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8281. Min Act: -0.1700

Data Index: 278871 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.7968. Min Act: -0.1700

Data Index: 63749 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 4.2971. Min Range: -4.2971

Max Act: 3.8281. Min Act: -0.1700

Data Index: 628675 (C4 (Web Text))

Max Activating Token Index: 672