Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5762. Min Act: -0.1700
Data Index: 3680171 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5449. Min Act: -0.1700
Data Index: 6356892 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5449. Min Act: -0.1700
Data Index: 6277371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5449. Min Act: -0.1700
Data Index: 4112454 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5292. Min Act: -0.1700
Data Index: 5880513 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5292. Min Act: -0.1700
Data Index: 5451731 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5449. Min Act: -0.1700
Data Index: 5428297 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5292. Min Act: -0.1700
Data Index: 2980216 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5292. Min Act: -0.1700
Data Index: 2974322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5292. Min Act: -0.1700
Data Index: 8666175 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5292. Min Act: -0.1700
Data Index: 6733841 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5292. Min Act: -0.1700
Data Index: 1004737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5136. Min Act: -0.1700
Data Index: 2956260 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5136. Min Act: -0.1700
Data Index: 2751490 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.5136. Min Act: -0.1700
Data Index: 4185582 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.4979. Min Act: -0.1700
Data Index: 4296323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.4979. Min Act: -0.1700
Data Index: 4879034 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.4979. Min Act: -0.1700
Data Index: 5352851 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.4979. Min Act: -0.1700
Data Index: 5563295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5762. Min Range: -3.5762
Max Act: 3.4979. Min Act: -0.1700
Data Index: 6014296 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19