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

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

Neuron 1210 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.2745. Min Act: -0.1700

Data Index: 300043 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.2120. Min Act: -0.1700

Data Index: 422980 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.1495. Min Act: -0.1700

Data Index: 393037 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0558. Min Act: -0.1700

Data Index: 222589 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.1183. Min Act: -0.1700

Data Index: 480319 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0870. Min Act: -0.1700

Data Index: 228096 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0870. Min Act: -0.1700

Data Index: 1319796 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0558. Min Act: -0.1700

Data Index: 771526 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0558. Min Act: -0.1700

Data Index: 393753 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0245. Min Act: -0.1700

Data Index: 1353251 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0558. Min Act: -0.1700

Data Index: 880529 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0245. Min Act: -0.1700

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 5.2745. Min Range: -5.2745

Max Act: 5.0245. Min Act: -0.1700

Data Index: 1164051 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 5.2745. Min Range: -5.2745

Max Act: 4.9308. Min Act: -0.1700

Data Index: 860713 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 5.2745. Min Range: -5.2745

Max Act: 4.9308. Min Act: -0.1700

Data Index: 5621 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 5.2745. Min Range: -5.2745

Max Act: 4.9620. Min Act: -0.1700

Data Index: 858005 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 5.2745. Min Range: -5.2745

Max Act: 4.9933. Min Act: -0.1700

Data Index: 295724 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 5.2745. Min Range: -5.2745

Max Act: 4.9620. Min Act: -0.1700

Data Index: 789843 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 5.2745. Min Range: -5.2745

Max Act: 4.9933. Min Act: -0.1700

Data Index: 1069727 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 5.2745. Min Range: -5.2745

Max Act: 4.9308. Min Act: -0.1700

Data Index: 939326 (C4 (Web Text))

Max Activating Token Index: 624