Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2156. Min Range: -7.2156
Max Act: 7.2156. Min Act: -0.1700
Data Index: 3772926 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2156. Min Range: -7.2156
Max Act: 7.0281. Min Act: -0.1700
Data Index: 3353886 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.9656. Min Act: -0.1700
Data Index: 544758 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.8406. Min Act: -0.1700
Data Index: 3238720 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.8406. Min Act: -0.1700
Data Index: 2976180 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7781. Min Act: -0.1700
Data Index: 966503 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7781. Min Act: -0.1700
Data Index: 335164 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6843. Min Act: -0.1700
Data Index: 5011501 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7156. Min Act: -0.1700
Data Index: 3114528 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7156. Min Act: -0.1700
Data Index: 764815 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.7156. Min Act: -0.1700
Data Index: 2983814 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6843. Min Act: -0.1700
Data Index: 704610 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 4212482 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6218. Min Act: -0.1700
Data Index: 2177456 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 7072069 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 221384 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 6034589 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 1222085 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6218. Min Act: -0.1700
Data Index: 118416 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2156. Min Range: -7.2156
Max Act: 6.6218. Min Act: -0.1700
Data Index: 3879761 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19