Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1688 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1510. Min Range: -4.1510
Max Act: 4.1510. Min Act: -0.1700
Data Index: 1517628 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.9010. Min Act: -0.1700
Data Index: 1780728 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.8697. Min Act: -0.1700
Data Index: 5833495 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.8697. Min Act: -0.1700
Data Index: 3144277 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.8072. Min Act: -0.1700
Data Index: 1335743 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.8072. Min Act: -0.1700
Data Index: 8763136 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.8072. Min Act: -0.1700
Data Index: 4242573 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.8072. Min Act: -0.1700
Data Index: 73713 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7759. Min Act: -0.1700
Data Index: 2389580 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7446. Min Act: -0.1700
Data Index: 1145413 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7446. Min Act: -0.1700
Data Index: 1668607 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7446. Min Act: -0.1700
Data Index: 4593777 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7446. Min Act: -0.1700
Data Index: 7521533 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7133. Min Act: -0.1700
Data Index: 7413042 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7133. Min Act: -0.1700
Data Index: 3660250 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7133. Min Act: -0.1700
Data Index: 1105644 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.6820. Min Act: -0.1700
Data Index: 1668610 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.7133. Min Act: -0.1700
Data Index: 1845829 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.6820. Min Act: -0.1700
Data Index: 5182957 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1510. Min Range: -4.1510
Max Act: 3.6820. Min Act: -0.1700
Data Index: 366079 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19