Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.9900. Min Act: -0.1700
Data Index: 3450076 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.8650. Min Act: -0.1700
Data Index: 1713743 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.8025. Min Act: -0.1700
Data Index: 5569653 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6775. Min Act: -0.1700
Data Index: 4171839 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1699
Data Index: 5162664 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6775. Min Act: -0.1700
Data Index: 168415 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6775. Min Act: -0.1700
Data Index: 7835855 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6775. Min Act: -0.1700
Data Index: 3735901 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6775. Min Act: -0.1700
Data Index: 1486446 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6775. Min Act: -0.1700
Data Index: 1636595 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1700
Data Index: 8543267 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6775. Min Act: -0.1700
Data Index: 1483292 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1700
Data Index: 8164290 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1700
Data Index: 834225 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1700
Data Index: 4888852 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1700
Data Index: 7634206 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1700
Data Index: 6805151 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1700
Data Index: 3618839 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.6150. Min Act: -0.1700
Data Index: 5137415 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9900. Min Range: -7.9900
Max Act: 7.5525. Min Act: -0.1700
Data Index: 6905941 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19