Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2057 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.7376. Min Act: -0.1700
Data Index: 1053689 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.6438. Min Act: -0.1700
Data Index: 7629177 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.2688. Min Act: -0.1700
Data Index: 4156734 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.2063. Min Act: -0.1700
Data Index: 3168126 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.2063. Min Act: -0.1700
Data Index: 1012087 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.2376. Min Act: -0.1700
Data Index: 5722108 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1438. Min Act: -0.1700
Data Index: 8235961 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1438. Min Act: -0.1700
Data Index: 8748093 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1438. Min Act: -0.1700
Data Index: 3777248 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1126. Min Act: -0.1700
Data Index: 3846460 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.1126. Min Act: -0.1700
Data Index: 5217083 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0813. Min Act: -0.1700
Data Index: 229473 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0501. Min Act: -0.1700
Data Index: 2954837 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0501. Min Act: -0.1700
Data Index: 5692010 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0501. Min Act: -0.1700
Data Index: 7268022 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0501. Min Act: -0.1700
Data Index: 3815751 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0501. Min Act: -0.1700
Data Index: 6704401 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7376. Min Range: -6.7376
Max Act: 6.0501. Min Act: -0.1700
Data Index: 8725195 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7376. Min Range: -6.7376
Max Act: 5.9563. Min Act: -0.1700
Data Index: 474343 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7376. Min Range: -6.7376
Max Act: 5.9876. Min Act: -0.1700
Data Index: 1613962 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19