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

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

Neuron 1434 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1902. Min Range: -3.1902

Max Act: 3.1902. Min Act: -0.1700

Data Index: 400257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.8425. Min Act: -0.1700

Data Index: 76757 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.8583. Min Act: -0.1700

Data Index: 1095211 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.8265. Min Act: -0.1700

Data Index: 235105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.7628. Min Act: -0.1700

Data Index: 1135585 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.6829. Min Act: -0.1700

Data Index: 1230036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.6829. Min Act: -0.1700

Data Index: 1271354 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.6508. Min Act: -0.1700

Data Index: 767284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.6187. Min Act: -0.1700

Data Index: 376276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.6187. Min Act: -0.1675

Data Index: 451579 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5704. Min Act: -0.1700

Data Index: 577665 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5704. Min Act: -0.1700

Data Index: 846919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5543. Min Act: -0.1700

Data Index: 321109 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5543. Min Act: -0.1700

Data Index: 712577 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5382. Min Act: -0.1700

Data Index: 706236 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5704. Min Act: -0.1700

Data Index: 430385 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5543. Min Act: -0.1700

Data Index: 690304 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5382. Min Act: -0.1700

Data Index: 103265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5058. Min Act: -0.1700

Data Index: 634008 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5058. Min Act: -0.1700

Data Index: 288038 (C4 (Web Text))

Max Activating Token Index: 1023