Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.1776. Min Act: -0.1700
Data Index: 1517297 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.1463. Min Act: -0.1700
Data Index: 3405166 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0838. Min Act: -0.1700
Data Index: 1292920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0526. Min Act: -0.1700
Data Index: 3450934 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0526. Min Act: -0.1700
Data Index: 7220103 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0526. Min Act: -0.1700
Data Index: 6464780 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0526. Min Act: -0.1700
Data Index: 706333 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0526. Min Act: -0.1700
Data Index: 3402639 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0526. Min Act: -0.1700
Data Index: 356690 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0213. Min Act: -0.1700
Data Index: 5193850 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0526. Min Act: -0.1700
Data Index: 3770891 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0213. Min Act: -0.1700
Data Index: 5177961 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0213. Min Act: -0.1700
Data Index: 383758 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1776. Min Range: -4.1776
Max Act: 4.0213. Min Act: -0.1700
Data Index: 896505 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1776. Min Range: -4.1776
Max Act: 3.9900. Min Act: -0.1700
Data Index: 1316648 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1776. Min Range: -4.1776
Max Act: 3.9900. Min Act: -0.1700
Data Index: 5522217 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1776. Min Range: -4.1776
Max Act: 3.9900. Min Act: -0.1700
Data Index: 4878370 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1776. Min Range: -4.1776
Max Act: 3.9900. Min Act: -0.1700
Data Index: 5648137 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1776. Min Range: -4.1776
Max Act: 3.9900. Min Act: -0.1700
Data Index: 1666968 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1776. Min Range: -4.1776
Max Act: 3.9900. Min Act: -0.1700
Data Index: 1004192 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19