Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.8957. Min Act: -0.1700
Data Index: 4367937 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.3332. Min Act: -0.1700
Data Index: 816174 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.2707. Min Act: -0.1700
Data Index: 944430 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.2707. Min Act: -0.1700
Data Index: 6740334 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.1457. Min Act: -0.1699
Data Index: 3753997 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.2082. Min Act: -0.1700
Data Index: 4475632 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.1457. Min Act: -0.1698
Data Index: 7785795 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.1457. Min Act: -0.1700
Data Index: 7672486 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.2082. Min Act: -0.1700
Data Index: 4665593 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.2082. Min Act: -0.1700
Data Index: 4629615 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.2082. Min Act: -0.1700
Data Index: 3555106 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.1457. Min Act: -0.1699
Data Index: 5386274 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.1457. Min Act: -0.1700
Data Index: 3735878 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.1457. Min Act: -0.1700
Data Index: 7001280 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.1457. Min Act: -0.1700
Data Index: 3877723 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.0832. Min Act: -0.1700
Data Index: 6516017 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.0832. Min Act: -0.1700
Data Index: 3047407 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.0832. Min Act: -0.1700
Data Index: 3387072 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.0832. Min Act: -0.1699
Data Index: 6966416 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8957. Min Range: -8.8957
Max Act: 8.0832. Min Act: -0.1700
Data Index: 720726 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19