Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 274 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.2828. Min Act: -0.1700

Data Index: 55594 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.1570. Min Act: -0.1700

Data Index: 608015 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.1727. Min Act: -0.1700

Data Index: 1539842 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.1412. Min Act: -0.1700

Data Index: 1301121 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.1412. Min Act: -0.1700

Data Index: 1477997 (Python Code)

Max Activating Token Index: 573

Text #5

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.1097. Min Act: -0.1700

Data Index: 1605571 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0940. Min Act: -0.1700

Data Index: 1580348 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0940. Min Act: -0.1700

Data Index: 647125 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0782. Min Act: -0.1700

Data Index: 1388818 (Python Code)

Max Activating Token Index: 576

Text #9

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0782. Min Act: -0.1700

Data Index: 1602452 (Python Code)

Max Activating Token Index: 532

Text #10

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0782. Min Act: -0.1700

Data Index: 639044 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0624. Min Act: -0.1700

Data Index: 1413726 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0624. Min Act: -0.1700

Data Index: 1648522 (Python Code)

Max Activating Token Index: 371

Text #13

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0624. Min Act: -0.1700

Data Index: 1440510 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0624. Min Act: -0.1700

Data Index: 153322 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0624. Min Act: -0.1700

Data Index: 1432351 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1442421 (Python Code)

Max Activating Token Index: 298

Text #17

Max Range: 3.2828. Min Range: -3.2828

Max Act: 2.9992. Min Act: -0.1700

Data Index: 1475389 (Python Code)

Max Activating Token Index: 620

Text #18

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0466. Min Act: -0.1700

Data Index: 1430208 (Python Code)

Max Activating Token Index: 778

Text #19

Max Range: 3.2828. Min Range: -3.2828

Max Act: 3.0150. Min Act: -0.1700

Data Index: 771579 (C4 (Web Text))

Max Activating Token Index: 406