Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7687. Min Act: -0.1700
Data Index: 6235682 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.8000. Min Act: -0.1700
Data Index: 8070461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7687. Min Act: -0.1700
Data Index: 747283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7375. Min Act: -0.1700
Data Index: 5644237 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7375. Min Act: -0.1700
Data Index: 1564686 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7375. Min Act: -0.1700
Data Index: 8358158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7375. Min Act: -0.1700
Data Index: 1087387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7062. Min Act: -0.1700
Data Index: 4300397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7062. Min Act: -0.1700
Data Index: 5227325 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.7062. Min Act: -0.1700
Data Index: 5298679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6749. Min Act: -0.1700
Data Index: 5176585 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6749. Min Act: -0.1700
Data Index: 334097 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6749. Min Act: -0.1700
Data Index: 1252603 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6749. Min Act: -0.1700
Data Index: 1843518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6436. Min Act: -0.1700
Data Index: 3225710 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6436. Min Act: -0.1700
Data Index: 4633679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6436. Min Act: -0.1700
Data Index: 5036845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6436. Min Act: -0.1700
Data Index: 327027 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6436. Min Act: -0.1700
Data Index: 1853411 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8000. Min Range: -3.8000
Max Act: 3.6436. Min Act: -0.1700
Data Index: 347850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19