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

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

Neuron 883 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.9033. Min Act: -0.1700

Data Index: 1115493 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8721. Min Act: -0.1700

Data Index: 390101 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8721. Min Act: -0.1700

Data Index: 164010 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8408. Min Act: -0.1700

Data Index: 1109345 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8095. Min Act: -0.1700

Data Index: 153312 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8095. Min Act: -0.1700

Data Index: 161216 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8095. Min Act: -0.1700

Data Index: 235777 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 647297 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 1053796 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 181325 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 195808 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7469. Min Act: -0.1700

Data Index: 520969 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 34734 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 216563 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 589197 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7469. Min Act: -0.1700

Data Index: 24696 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 1046702 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 1149100 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8095. Min Act: -0.1700

Data Index: 86296 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 1195382 (C4 (Web Text))

Max Activating Token Index: 909