Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3881 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1004. Min Range: -7.1004
Max Act: 7.1004. Min Act: -0.1700
Data Index: 7208135 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1004. Min Range: -7.1004
Max Act: 7.0067. Min Act: -0.1700
Data Index: 2503861 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.9754. Min Act: -0.1700
Data Index: 1499959 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.9442. Min Act: -0.1700
Data Index: 7371738 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.8817. Min Act: -0.1700
Data Index: 8018125 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.8817. Min Act: -0.1700
Data Index: 1719837 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.8817. Min Act: -0.1700
Data Index: 6959266 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.7879. Min Act: -0.1699
Data Index: 5362747 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.7879. Min Act: -0.1700
Data Index: 884649 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.7879. Min Act: -0.1700
Data Index: 1189478 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.7567. Min Act: -0.1700
Data Index: 5511779 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.7254. Min Act: -0.1700
Data Index: 4654755 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.6629. Min Act: -0.1700
Data Index: 7201666 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.6942. Min Act: -0.1700
Data Index: 6780169 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.6317. Min Act: -0.1700
Data Index: 797641 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.6629. Min Act: -0.1700
Data Index: 5362748 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.6317. Min Act: -0.1700
Data Index: 3859292 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.6629. Min Act: -0.1700
Data Index: 4010298 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.6317. Min Act: -0.1700
Data Index: 5010906 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1004. Min Range: -7.1004
Max Act: 6.6317. Min Act: -0.1700
Data Index: 4938791 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19