Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.3883. Min Act: -0.1700
Data Index: 4888462 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.3883. Min Act: -0.1700
Data Index: 4809407 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.3258. Min Act: -0.1700
Data Index: 3189742 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.3258. Min Act: -0.1700
Data Index: 2341640 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.2008. Min Act: -0.1700
Data Index: 8490299 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.2008. Min Act: -0.1700
Data Index: 1786280 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.2008. Min Act: -0.1700
Data Index: 3227629 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.2008. Min Act: -0.1700
Data Index: 5962082 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.0758. Min Act: -0.1700
Data Index: 140340 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.0758. Min Act: -0.1700
Data Index: 4809409 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.0758. Min Act: -0.1700
Data Index: 7188660 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3883. Min Range: -8.3883
Max Act: 8.0445. Min Act: -0.1700
Data Index: 786687 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3883. Min Range: -8.3883
Max Act: 7.9820. Min Act: -0.1700
Data Index: 6060462 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3883. Min Range: -8.3883
Max Act: 7.9508. Min Act: -0.1700
Data Index: 2861804 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3883. Min Range: -8.3883
Max Act: 7.9508. Min Act: -0.1700
Data Index: 7774021 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3883. Min Range: -8.3883
Max Act: 7.8883. Min Act: -0.1700
Data Index: 3665844 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3883. Min Range: -8.3883
Max Act: 7.9195. Min Act: -0.1700
Data Index: 5740492 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3883. Min Range: -8.3883
Max Act: 7.8570. Min Act: -0.1700
Data Index: 3574568 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3883. Min Range: -8.3883
Max Act: 7.8570. Min Act: -0.1700
Data Index: 2729977 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3883. Min Range: -8.3883
Max Act: 7.8258. Min Act: -0.1700
Data Index: 1646094 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19