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

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

Neuron 1893 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: 3.2895. Min Range: -3.2895

Max Act: 3.2895. Min Act: -0.1700

Data Index: 1047852 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2895. Min Act: -0.1700

Data Index: 853237 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2423. Min Act: -0.1700

Data Index: 610609 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2423. Min Act: -0.1700

Data Index: 1353521 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2266. Min Act: -0.1700

Data Index: 591741 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2737. Min Act: -0.1700

Data Index: 829435 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2266. Min Act: -0.1700

Data Index: 261065 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2266. Min Act: -0.1700

Data Index: 373004 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2580. Min Act: -0.1700

Data Index: 903603 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2266. Min Act: -0.1700

Data Index: 1113797 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1951. Min Act: -0.1700

Data Index: 1264148 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2109. Min Act: -0.1700

Data Index: 768111 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2266. Min Act: -0.1700

Data Index: 321017 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1794. Min Act: -0.1700

Data Index: 316524 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1794. Min Act: -0.1700

Data Index: 146937 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1951. Min Act: -0.1700

Data Index: 761445 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1794. Min Act: -0.1700

Data Index: 851075 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1794. Min Act: -0.1700

Data Index: 249215 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1951. Min Act: -0.1700

Data Index: 47845 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1637. Min Act: -0.1700

Data Index: 665022 (C4 (Web Text))

Max Activating Token Index: 821