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

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

Neuron 383 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: 3.1843. Min Range: -3.1843

Max Act: 3.1843. Min Act: -0.1700

Data Index: 187447 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1371. Min Act: -0.1700

Data Index: 620062 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1371. Min Act: -0.1700

Data Index: 1261578 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1371. Min Act: -0.1700

Data Index: 893962 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1213. Min Act: -0.1700

Data Index: 759418 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1213. Min Act: -0.1700

Data Index: 661491 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1213. Min Act: -0.1700

Data Index: 249892 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1213. Min Act: -0.1700

Data Index: 790711 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1371. Min Act: -0.1700

Data Index: 1329401 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1213. Min Act: -0.1700

Data Index: 306927 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1056. Min Act: -0.1700

Data Index: 1286227 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.1056. Min Act: -0.1700

Data Index: 786800 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0898. Min Act: -0.1700

Data Index: 535166 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0898. Min Act: -0.1700

Data Index: 931813 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0740. Min Act: -0.1700

Data Index: 750754 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0740. Min Act: -0.1700

Data Index: 131445 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0740. Min Act: -0.1700

Data Index: 888905 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0898. Min Act: -0.1700

Data Index: 1051923 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0740. Min Act: -0.1700

Data Index: 1244242 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 3.1843. Min Range: -3.1843

Max Act: 3.0583. Min Act: -0.1700

Data Index: 838296 (C4 (Web Text))

Max Activating Token Index: 56