Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1857 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.7995. Min Act: -0.1700

Data Index: 558969 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.7682. Min Act: -0.1700

Data Index: 1142757 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.7682. Min Act: -0.1700

Data Index: 726052 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1165623 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6743. Min Act: -0.1700

Data Index: 586213 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.7056. Min Act: -0.1700

Data Index: 699400 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6743. Min Act: -0.1700

Data Index: 894745 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6430. Min Act: -0.1700

Data Index: 554077 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6117. Min Act: -0.1700

Data Index: 1136447 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6430. Min Act: -0.1700

Data Index: 1077250 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6430. Min Act: -0.1700

Data Index: 984814 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6117. Min Act: -0.1700

Data Index: 1216213 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6117. Min Act: -0.1700

Data Index: 676800 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6117. Min Act: -0.1700

Data Index: 1074996 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6117. Min Act: -0.1700

Data Index: 1053076 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6117. Min Act: -0.1700

Data Index: 863521 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6117. Min Act: -0.1700

Data Index: 339978 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.6117. Min Act: -0.1700

Data Index: 988610 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.5804. Min Act: -0.1700

Data Index: 827989 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 3.7995. Min Range: -3.7995

Max Act: 3.5491. Min Act: -0.1700

Data Index: 846426 (C4 (Web Text))

Max Activating Token Index: 870