Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0091. Min Range: -6.0091
Max Act: 6.0091. Min Act: -0.1700
Data Index: 2533334 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8528. Min Act: -0.1700
Data Index: 7255124 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8528. Min Act: -0.1700
Data Index: 1357251 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8528. Min Act: -0.1700
Data Index: 772197 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8528. Min Act: -0.1700
Data Index: 6718498 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8216. Min Act: -0.1700
Data Index: 8447088 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7903. Min Act: -0.1700
Data Index: 8465907 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8216. Min Act: -0.1700
Data Index: 7793249 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8216. Min Act: -0.1700
Data Index: 7806623 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8216. Min Act: -0.1700
Data Index: 5096838 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7903. Min Act: -0.1700
Data Index: 4868431 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7903. Min Act: -0.1700
Data Index: 2993813 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.8216. Min Act: -0.1700
Data Index: 8243329 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7591. Min Act: -0.1700
Data Index: 5564254 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7591. Min Act: -0.1700
Data Index: 800728 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7591. Min Act: -0.1700
Data Index: 99804 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7591. Min Act: -0.1700
Data Index: 1304569 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7591. Min Act: -0.1700
Data Index: 5028726 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7591. Min Act: -0.1700
Data Index: 6027980 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0091. Min Range: -6.0091
Max Act: 5.7903. Min Act: -0.1700
Data Index: 175146 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19