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

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

Neuron 1941 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: 5.3694. Min Range: -5.3694

Max Act: 5.3694. Min Act: -0.1700

Data Index: 12895 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.2757. Min Act: -0.1700

Data Index: 879828 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.1819. Min Act: -0.1700

Data Index: 619984 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.1507. Min Act: -0.1700

Data Index: 687713 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.0569. Min Act: -0.1700

Data Index: 1333426 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.0257. Min Act: -0.1700

Data Index: 731666 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.9632. Min Act: -0.1700

Data Index: 468795 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.9632. Min Act: -0.1700

Data Index: 663688 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.9632. Min Act: -0.1700

Data Index: 1250363 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.0569. Min Act: -0.1700

Data Index: 1089016 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.0257. Min Act: -0.1700

Data Index: 402547 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.0257. Min Act: -0.1700

Data Index: 594758 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 5.3694. Min Range: -5.3694

Max Act: 5.0257. Min Act: -0.1700

Data Index: 160638 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.9632. Min Act: -0.1700

Data Index: 1081356 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.9319. Min Act: -0.1700

Data Index: 1176148 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.7757. Min Act: -0.1700

Data Index: 811817 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.9007. Min Act: -0.1700

Data Index: 1024661 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.9007. Min Act: -0.1700

Data Index: 204648 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.9319. Min Act: -0.1700

Data Index: 1024759 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 5.3694. Min Range: -5.3694

Max Act: 4.8694. Min Act: -0.1700

Data Index: 1212929 (C4 (Web Text))

Max Activating Token Index: 548