Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.2719. Min Act: -0.1700
Data Index: 8213788 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0219. Min Act: -0.1700
Data Index: 3161928 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.9594. Min Act: -0.1700
Data Index: 1874071 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.9282. Min Act: -0.1700
Data Index: 8650522 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.9282. Min Act: -0.1700
Data Index: 3161929 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8969. Min Act: -0.1700
Data Index: 2653297 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8969. Min Act: -0.1700
Data Index: 6618520 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8969. Min Act: -0.1700
Data Index: 4990461 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8657. Min Act: -0.1700
Data Index: 6721560 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8657. Min Act: -0.1700
Data Index: 5438169 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8032. Min Act: -0.1700
Data Index: 7829822 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8032. Min Act: -0.1700
Data Index: 8362708 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8032. Min Act: -0.1700
Data Index: 1263936 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8032. Min Act: -0.1700
Data Index: 4937801 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.7719. Min Act: -0.1700
Data Index: 2111066 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8032. Min Act: -0.1700
Data Index: 7071719 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.7719. Min Act: -0.1700
Data Index: 1797040 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.7719. Min Act: -0.1700
Data Index: 2711074 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.7719. Min Act: -0.1700
Data Index: 7000029 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.7407. Min Act: -0.1700
Data Index: 6814938 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19