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

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

Neuron 487 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.2584. Min Act: -0.1700

Data Index: 1329464 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1955. Min Act: -0.1700

Data Index: 876806 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1955. Min Act: -0.1700

Data Index: 795499 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.2112. Min Act: -0.1700

Data Index: 990438 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1640. Min Act: -0.1700

Data Index: 798028 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1640. Min Act: -0.1700

Data Index: 253800 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1483. Min Act: -0.1700

Data Index: 859022 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1167. Min Act: -0.1700

Data Index: 378209 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1325. Min Act: -0.1700

Data Index: 251385 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1325. Min Act: -0.1700

Data Index: 110472 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1325. Min Act: -0.1700

Data Index: 853608 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1167. Min Act: -0.1700

Data Index: 659674 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1167. Min Act: -0.1700

Data Index: 262940 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0852. Min Act: -0.1700

Data Index: 892573 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1010. Min Act: -0.1700

Data Index: 1218118 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.1010. Min Act: -0.1700

Data Index: 1201897 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0694. Min Act: -0.1700

Data Index: 99882 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0694. Min Act: -0.1700

Data Index: 348171 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0852. Min Act: -0.1700

Data Index: 948833 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 3.2584. Min Range: -3.2584

Max Act: 3.0694. Min Act: -0.1700

Data Index: 219602 (C4 (Web Text))

Max Activating Token Index: 415