Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.8691. Min Act: -0.1700
Data Index: 1848927 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.8066. Min Act: -0.1700
Data Index: 8294131 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.8066. Min Act: -0.1700
Data Index: 6635893 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.7754. Min Act: -0.1700
Data Index: 7136978 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.7441. Min Act: -0.1700
Data Index: 2552502 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.7129. Min Act: -0.1700
Data Index: 8595665 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1104752 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.6816. Min Act: -0.1700
Data Index: 1371673 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.6504. Min Act: -0.1700
Data Index: 6495182 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.6191. Min Act: -0.1700
Data Index: 616231 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.5879. Min Act: -0.1700
Data Index: 4187392 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.6191. Min Act: -0.1700
Data Index: 1264514 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.6191. Min Act: -0.1700
Data Index: 6635889 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.5879. Min Act: -0.1700
Data Index: 7435719 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.5879. Min Act: -0.1700
Data Index: 896618 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.5879. Min Act: -0.1700
Data Index: 3357863 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.5566. Min Act: -0.1700
Data Index: 6587400 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.5566. Min Act: -0.1700
Data Index: 4244404 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.5566. Min Act: -0.1700
Data Index: 5327660 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8691. Min Range: -6.8691
Max Act: 6.5566. Min Act: -0.1700
Data Index: 1456712 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19