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

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

Neuron 957 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.6744. Min Act: -0.1700

Data Index: 995417 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.6744. Min Act: -0.1700

Data Index: 103321 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.6431. Min Act: -0.1700

Data Index: 1338378 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.6431. Min Act: -0.1700

Data Index: 82113 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.6118. Min Act: -0.1700

Data Index: 842698 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5805. Min Act: -0.1700

Data Index: 236554 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5178. Min Act: -0.1700

Data Index: 276483 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5178. Min Act: -0.1700

Data Index: 1236047 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5491. Min Act: -0.1700

Data Index: 785921 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5491. Min Act: -0.1700

Data Index: 1160871 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.4865. Min Act: -0.1700

Data Index: 459815 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5178. Min Act: -0.1700

Data Index: 846360 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5491. Min Act: -0.1700

Data Index: 13160 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5491. Min Act: -0.1700

Data Index: 325625 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5178. Min Act: -0.1700

Data Index: 792237 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5178. Min Act: -0.1700

Data Index: 1160647 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5178. Min Act: -0.1700

Data Index: 400883 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.4865. Min Act: -0.1700

Data Index: 105178 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.4865. Min Act: -0.1700

Data Index: 19749 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 3.6744. Min Range: -3.6744

Max Act: 3.5178. Min Act: -0.1700

Data Index: 431459 (C4 (Web Text))

Max Activating Token Index: 833