Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.9100. Min Act: -0.1700
Data Index: 778745 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.7225. Min Act: -0.1700
Data Index: 3644728 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.7225. Min Act: -0.1700
Data Index: 732420 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.5975. Min Act: -0.1700
Data Index: 8340687 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.5350. Min Act: -0.1700
Data Index: 4886795 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.5350. Min Act: -0.1700
Data Index: 6360621 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.5350. Min Act: -0.1700
Data Index: 6360620 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.5350. Min Act: -0.1700
Data Index: 1612333 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.4725. Min Act: -0.1700
Data Index: 4848460 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.4725. Min Act: -0.1700
Data Index: 4351534 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.4100. Min Act: -0.1700
Data Index: 7775950 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.3475. Min Act: -0.1700
Data Index: 2110779 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.3475. Min Act: -0.1700
Data Index: 7708832 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.2850. Min Act: -0.1700
Data Index: 2110782 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.2850. Min Act: -0.1700
Data Index: 6072464 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.2850. Min Act: -0.1700
Data Index: 4241910 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.2225. Min Act: -0.1700
Data Index: 3088049 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.2225. Min Act: -0.1700
Data Index: 2344981 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.2225. Min Act: -0.1700
Data Index: 6081815 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9100. Min Range: -8.9100
Max Act: 8.2225. Min Act: -0.1700
Data Index: 4768892 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19