Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9988. Min Act: -0.1700
Data Index: 6325331 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0301. Min Range: -5.0301
Max Act: 5.0301. Min Act: -0.1700
Data Index: 4523707 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9676. Min Act: -0.1700
Data Index: 666795 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9676. Min Act: -0.1700
Data Index: 7644653 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 955830 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9363. Min Act: -0.1700
Data Index: 7982120 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 1522754 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 3541016 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9363. Min Act: -0.1700
Data Index: 6002888 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8738. Min Act: -0.1700
Data Index: 531748 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 3903972 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9363. Min Act: -0.1700
Data Index: 5335319 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9363. Min Act: -0.1700
Data Index: 5899442 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 6326501 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 2212060 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 5192325 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 6572626 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8738. Min Act: -0.1700
Data Index: 3113062 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8738. Min Act: -0.1700
Data Index: 1228318 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 7476305 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19