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

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

Neuron 520 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: 5.4072. Min Range: -5.4072

Max Act: 5.4072. Min Act: -0.1700

Data Index: 958704 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.9384. Min Act: -0.1700

Data Index: 572360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.9697. Min Act: -0.1700

Data Index: 163535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.9384. Min Act: -0.1700

Data Index: 859493 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.9072. Min Act: -0.1700

Data Index: 1328498 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.8447. Min Act: -0.1700

Data Index: 94268 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.8759. Min Act: -0.1700

Data Index: 650755 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.8134. Min Act: -0.1700

Data Index: 1348564 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.8447. Min Act: -0.1700

Data Index: 776073 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.8134. Min Act: -0.1700

Data Index: 420236 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.8759. Min Act: -0.1700

Data Index: 966775 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.8447. Min Act: -0.1700

Data Index: 11299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.7822. Min Act: -0.1700

Data Index: 403390 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.7509. Min Act: -0.1700

Data Index: 757587 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.6884. Min Act: -0.1700

Data Index: 575742 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.7197. Min Act: -0.1700

Data Index: 509253 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.7509. Min Act: -0.1700

Data Index: 169688 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.7197. Min Act: -0.1700

Data Index: 1101470 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.6884. Min Act: -0.1700

Data Index: 24024 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 5.4072. Min Range: -5.4072

Max Act: 4.6884. Min Act: -0.1700

Data Index: 725840 (C4 (Web Text))

Max Activating Token Index: 549