Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3706 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1091. Min Range: -5.1091
Max Act: 5.1091. Min Act: -0.1700
Data Index: 7009149 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1091. Min Range: -5.1091
Max Act: 5.0466. Min Act: -0.1700
Data Index: 769843 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.9528. Min Act: -0.1700
Data Index: 5604052 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.8903. Min Act: -0.1700
Data Index: 4782484 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.8591. Min Act: -0.1700
Data Index: 372436 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.8903. Min Act: -0.1700
Data Index: 7184639 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.8278. Min Act: -0.1700
Data Index: 3214863 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.8278. Min Act: -0.1700
Data Index: 769835 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.8278. Min Act: -0.1700
Data Index: 6733961 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7653. Min Act: -0.1700
Data Index: 2039208 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7028. Min Act: -0.1700
Data Index: 5617801 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7028. Min Act: -0.1700
Data Index: 7365879 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7653. Min Act: -0.1700
Data Index: 4299608 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7653. Min Act: -0.1700
Data Index: 6737285 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7341. Min Act: -0.1700
Data Index: 5897016 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7653. Min Act: -0.1700
Data Index: 5897017 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7966. Min Act: -0.1700
Data Index: 917889 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.6716. Min Act: -0.1700
Data Index: 6737281 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7028. Min Act: -0.1700
Data Index: 8532747 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1091. Min Range: -5.1091
Max Act: 4.7653. Min Act: -0.1700
Data Index: 5857070 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19