Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4359. Min Range: -7.4359
Max Act: 7.4359. Min Act: -0.1700
Data Index: 5970691 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4359. Min Range: -7.4359
Max Act: 7.3734. Min Act: -0.1700
Data Index: 6462661 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4359. Min Range: -7.4359
Max Act: 7.1859. Min Act: -0.1700
Data Index: 1288250 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4359. Min Range: -7.4359
Max Act: 7.0922. Min Act: -0.1700
Data Index: 7463079 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4359. Min Range: -7.4359
Max Act: 7.0609. Min Act: -0.1700
Data Index: 6274136 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4359. Min Range: -7.4359
Max Act: 7.0609. Min Act: -0.1700
Data Index: 6204931 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.9984. Min Act: -0.1700
Data Index: 6112817 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.9672. Min Act: -0.1700
Data Index: 1802686 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.9359. Min Act: -0.1700
Data Index: 4085027 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.9672. Min Act: -0.1700
Data Index: 7334739 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.9047. Min Act: -0.1700
Data Index: 2587973 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.9047. Min Act: -0.1700
Data Index: 2049176 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.8734. Min Act: -0.1700
Data Index: 3592386 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.8422. Min Act: -0.1700
Data Index: 4620040 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.8422. Min Act: -0.1700
Data Index: 8140499 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.7797. Min Act: -0.1700
Data Index: 4725130 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.8109. Min Act: -0.1700
Data Index: 7494082 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.7797. Min Act: -0.1700
Data Index: 3893213 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.7484. Min Act: -0.1700
Data Index: 3229486 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4359. Min Range: -7.4359
Max Act: 6.7484. Min Act: -0.1700
Data Index: 1374504 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19