Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8881. Min Act: -0.1700
Data Index: 3121786 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7318. Min Act: -0.1700
Data Index: 3121785 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.6380. Min Act: -0.1700
Data Index: 3877815 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.4818. Min Act: -0.1700
Data Index: 8116153 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.4505. Min Act: -0.1700
Data Index: 3754338 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.3568. Min Act: -0.1700
Data Index: 1842446 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.3568. Min Act: -0.1700
Data Index: 1842447 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.3880. Min Act: -0.1700
Data Index: 8116156 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.3255. Min Act: -0.1700
Data Index: 7851308 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.3255. Min Act: -0.1700
Data Index: 1719692 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2630. Min Act: -0.1700
Data Index: 5391655 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2630. Min Act: -0.1700
Data Index: 3635350 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2630. Min Act: -0.1700
Data Index: 398073 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2318. Min Act: -0.1700
Data Index: 8116155 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2318. Min Act: -0.1700
Data Index: 3126303 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2318. Min Act: -0.1700
Data Index: 5198954 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2005. Min Act: -0.1700
Data Index: 2033097 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2005. Min Act: -0.1700
Data Index: 6994632 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2005. Min Act: -0.1700
Data Index: 2395187 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.2005. Min Act: -0.1700
Data Index: 3279648 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19