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

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

Neuron 822 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: 3.2246. Min Range: -3.2246

Max Act: 3.2246. Min Act: -0.1700

Data Index: 278774 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1302. Min Act: -0.1700

Data Index: 648126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1460. Min Act: -0.1700

Data Index: 1479800 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1144. Min Act: -0.1700

Data Index: 384915 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1460. Min Act: -0.1700

Data Index: 1642194 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.2089. Min Act: -0.1700

Data Index: 1517975 (Python Code)

Max Activating Token Index: 647

Text #6

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.0513. Min Act: -0.1700

Data Index: 1423053 (Python Code)

Max Activating Token Index: 783

Text #7

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1617. Min Act: -0.1700

Data Index: 1440100 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1144. Min Act: -0.1700

Data Index: 1619457 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1460. Min Act: -0.1700

Data Index: 1608960 (Python Code)

Max Activating Token Index: 450

Text #10

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1144. Min Act: -0.1700

Data Index: 1461614 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1302. Min Act: -0.1700

Data Index: 1444915 (Python Code)

Max Activating Token Index: 838

Text #12

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1774. Min Act: -0.1700

Data Index: 1556469 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1144. Min Act: -0.1700

Data Index: 1592673 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1302. Min Act: -0.1700

Data Index: 1432617 (Python Code)

Max Activating Token Index: 572

Text #15

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.0671. Min Act: -0.1700

Data Index: 1552261 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.0987. Min Act: -0.1700

Data Index: 461655 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.0829. Min Act: -0.1700

Data Index: 1437755 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.0513. Min Act: -0.1700

Data Index: 1445598 (Python Code)

Max Activating Token Index: 272

Text #19

Max Range: 3.2246. Min Range: -3.2246

Max Act: 3.1302. Min Act: -0.1700

Data Index: 1507745 (Python Code)

Max Activating Token Index: 956