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

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

Neuron 266 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: 5.3019. Min Range: -5.3019

Max Act: 5.3019. Min Act: -0.1700

Data Index: 1245102 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.2707. Min Act: -0.1700

Data Index: 992714 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.2707. Min Act: -0.1700

Data Index: 876983 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1769. Min Act: -0.1700

Data Index: 886220 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1457. Min Act: -0.1700

Data Index: 1070039 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1769. Min Act: -0.1700

Data Index: 565201 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1457. Min Act: -0.1700

Data Index: 692136 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1457. Min Act: -0.1700

Data Index: 43569 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1144. Min Act: -0.1700

Data Index: 125324 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1457. Min Act: -0.1700

Data Index: 1357151 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.0832. Min Act: -0.1700

Data Index: 1171486 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.0832. Min Act: -0.1700

Data Index: 1296608 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1144. Min Act: -0.1700

Data Index: 1222201 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.1144. Min Act: -0.1700

Data Index: 1193908 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.0207. Min Act: -0.1700

Data Index: 86274 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.0207. Min Act: -0.1700

Data Index: 154595 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.0519. Min Act: -0.1700

Data Index: 206507 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 5.3019. Min Range: -5.3019

Max Act: 4.9582. Min Act: -0.1700

Data Index: 942594 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 5.3019. Min Range: -5.3019

Max Act: 4.9894. Min Act: -0.1700

Data Index: 428165 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 5.3019. Min Range: -5.3019

Max Act: 5.0207. Min Act: -0.1700

Data Index: 441507 (C4 (Web Text))

Max Activating Token Index: 47