Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.4344. Min Act: -0.1700
Data Index: 6017539 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.3094. Min Act: -0.1700
Data Index: 2039438 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.1844. Min Act: -0.1700
Data Index: 5128072 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.2157. Min Act: -0.1700
Data Index: 3747034 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.1844. Min Act: -0.1700
Data Index: 1107317 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.1532. Min Act: -0.1700
Data Index: 7235265 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.1532. Min Act: -0.1700
Data Index: 2010115 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.1532. Min Act: -0.1700
Data Index: 8430050 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0906. Min Act: -0.1700
Data Index: 8347198 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.1219. Min Act: -0.1700
Data Index: 5320123 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0906. Min Act: -0.1700
Data Index: 4717911 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0906. Min Act: -0.1700
Data Index: 6472517 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0906. Min Act: -0.1700
Data Index: 7691949 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0906. Min Act: -0.1700
Data Index: 7156420 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0906. Min Act: -0.1700
Data Index: 7197230 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0906. Min Act: -0.1700
Data Index: 8350659 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0594. Min Act: -0.1700
Data Index: 1510478 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0594. Min Act: -0.1700
Data Index: 963948 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0594. Min Act: -0.1700
Data Index: 3448918 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4344. Min Range: -4.4344
Max Act: 4.0594. Min Act: -0.1700
Data Index: 6802486 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19