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

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

Neuron 1293 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: 5.1910. Min Range: -5.1910

Max Act: 5.1910. Min Act: -0.1700

Data Index: 258384 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 5.1910. Min Range: -5.1910

Max Act: 5.1598. Min Act: -0.1700

Data Index: 1173979 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 5.1910. Min Range: -5.1910

Max Act: 5.0660. Min Act: -0.1700

Data Index: 658317 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.9410. Min Act: -0.1700

Data Index: 148897 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.9410. Min Act: -0.1700

Data Index: 704231 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.8473. Min Act: -0.1700

Data Index: 1109243 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.8473. Min Act: -0.1700

Data Index: 533337 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7535. Min Act: -0.1700

Data Index: 944147 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.8473. Min Act: -0.1700

Data Index: 1205726 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.8473. Min Act: -0.1698

Data Index: 626932 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7535. Min Act: -0.1700

Data Index: 463114 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7535. Min Act: -0.1700

Data Index: 899022 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7535. Min Act: -0.1700

Data Index: 696495 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7848. Min Act: -0.1700

Data Index: 46924 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.6910. Min Act: -0.1700

Data Index: 195910 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7535. Min Act: -0.1700

Data Index: 1270844 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7535. Min Act: -0.1700

Data Index: 1179317 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7535. Min Act: -0.1700

Data Index: 901720 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.7535. Min Act: -0.1700

Data Index: 1131502 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 5.1910. Min Range: -5.1910

Max Act: 4.6910. Min Act: -0.1700

Data Index: 691803 (C4 (Web Text))

Max Activating Token Index: 640