Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2247 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0082. Min Range: -10.0082
Max Act: 10.0082. Min Act: -0.1700
Data Index: 388036 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.8832. Min Act: -0.1700
Data Index: 1210480 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.7582. Min Act: -0.1700
Data Index: 7169039 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.5082. Min Act: -0.1700
Data Index: 6776904 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.5082. Min Act: -0.1700
Data Index: 8033238 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.3207. Min Act: -0.1700
Data Index: 1648967 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.3832. Min Act: -0.1700
Data Index: 3349622 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.3832. Min Act: -0.1700
Data Index: 4189844 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.2582. Min Act: -0.1700
Data Index: 3592239 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.1957. Min Act: -0.1700
Data Index: 8005555 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.1332. Min Act: -0.1700
Data Index: 294006 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.0082. Min Act: -0.1700
Data Index: 7188643 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.0082. Min Act: -0.1700
Data Index: 1751653 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.0082. Min Act: -0.1700
Data Index: 2126321 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0082. Min Range: -10.0082
Max Act: 9.0082. Min Act: -0.1700
Data Index: 5084193 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0082. Min Range: -10.0082
Max Act: 8.9457. Min Act: -0.1700
Data Index: 8424597 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0082. Min Range: -10.0082
Max Act: 8.9457. Min Act: -0.1700
Data Index: 7083569 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0082. Min Range: -10.0082
Max Act: 8.8832. Min Act: -0.1700
Data Index: 4918004 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0082. Min Range: -10.0082
Max Act: 8.8832. Min Act: -0.1700
Data Index: 7078168 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0082. Min Range: -10.0082
Max Act: 8.9457. Min Act: -0.1700
Data Index: 4823163 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19