Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.3405. Min Act: -0.1700
Data Index: 2613106 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2748. Min Act: -0.1700
Data Index: 1697808 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2748. Min Act: -0.1700
Data Index: 5680933 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1754. Min Act: -0.1700
Data Index: 8236740 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1920. Min Act: -0.1700
Data Index: 4976552 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1588. Min Act: -0.1700
Data Index: 2372 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1588. Min Act: -0.1700
Data Index: 5948580 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1588. Min Act: -0.1700
Data Index: 381010 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1421. Min Act: -0.1700
Data Index: 273185 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1421. Min Act: -0.1700
Data Index: 2827501 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1254. Min Act: -0.1700
Data Index: 4696276 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1087. Min Act: -0.1700
Data Index: 1605029 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1087. Min Act: -0.1700
Data Index: 840133 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1087. Min Act: -0.1700
Data Index: 4544778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1087. Min Act: -0.1700
Data Index: 5082225 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1087. Min Act: -0.1700
Data Index: 3340304 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.0919. Min Act: -0.1700
Data Index: 1851215 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.0919. Min Act: -0.1700
Data Index: 152459 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.0919. Min Act: -0.1700
Data Index: 7507916 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.0919. Min Act: -0.1700
Data Index: 3101108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19