Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.4046. Min Act: -0.1700
Data Index: 874897 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.4046. Min Act: -0.1700
Data Index: 7698120 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.3733. Min Act: -0.1700
Data Index: 5607061 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.3108. Min Act: -0.1700
Data Index: 2795010 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.3108. Min Act: -0.1700
Data Index: 1978984 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.2483. Min Act: -0.1700
Data Index: 228858 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.2483. Min Act: -0.1700
Data Index: 6246841 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1858. Min Act: -0.1700
Data Index: 3856053 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1858. Min Act: -0.1700
Data Index: 6420226 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1858. Min Act: -0.1700
Data Index: 3369210 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.2171. Min Act: -0.1700
Data Index: 6755167 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1858. Min Act: -0.1700
Data Index: 5803315 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1858. Min Act: -0.1700
Data Index: 2036937 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1546. Min Act: -0.1700
Data Index: 1246519 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1858. Min Act: -0.1700
Data Index: 7338912 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1233. Min Act: -0.1700
Data Index: 6595266 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1858. Min Act: -0.1700
Data Index: 6218210 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1546. Min Act: -0.1700
Data Index: 1432733 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1546. Min Act: -0.1700
Data Index: 8092223 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4046. Min Range: -7.4046
Max Act: 7.1546. Min Act: -0.1700
Data Index: 8301149 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19