Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1742 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.9201. Min Act: -0.1700
Data Index: 187235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8944. Min Act: -0.1700
Data Index: 7549930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.9030. Min Act: -0.1700
Data Index: 8678710 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8944. Min Act: -0.1700
Data Index: 7328882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8859. Min Act: -0.1700
Data Index: 2748458 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8773. Min Act: -0.1700
Data Index: 4177804 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8859. Min Act: -0.1700
Data Index: 4001335 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8859. Min Act: -0.1700
Data Index: 5612996 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8859. Min Act: -0.1700
Data Index: 404878 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8859. Min Act: -0.1700
Data Index: 2230388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8859. Min Act: -0.1700
Data Index: 307625 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8603. Min Act: -0.1700
Data Index: 5815479 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8688. Min Act: -0.1700
Data Index: 8634866 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8688. Min Act: -0.1700
Data Index: 2219106 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8688. Min Act: -0.1700
Data Index: 7281384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8603. Min Act: -0.1700
Data Index: 3671490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8603. Min Act: -0.1700
Data Index: 12923 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8518. Min Act: -0.1700
Data Index: 4561263 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8518. Min Act: -0.1700
Data Index: 7782470 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9201. Min Range: -0.9201
Max Act: 0.8518. Min Act: -0.1700
Data Index: 6920774 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19