Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.9593. Min Act: -0.1700
Data Index: 4851753 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.8968. Min Act: -0.1700
Data Index: 7816742 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.7718. Min Act: -0.1700
Data Index: 5699037 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.7093. Min Act: -0.1700
Data Index: 8794323 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.7093. Min Act: -0.1700
Data Index: 757427 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.7093. Min Act: -0.1700
Data Index: 7462770 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.7093. Min Act: -0.1700
Data Index: 5226270 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6468. Min Act: -0.1700
Data Index: 5085279 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6781. Min Act: -0.1700
Data Index: 725664 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6781. Min Act: -0.1700
Data Index: 5335817 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6156. Min Act: -0.1700
Data Index: 5397218 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6156. Min Act: -0.1700
Data Index: 6757996 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6156. Min Act: -0.1700
Data Index: 5511673 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6156. Min Act: -0.1700
Data Index: 3303729 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6156. Min Act: -0.1700
Data Index: 4534655 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.6156. Min Act: -0.1700
Data Index: 6380476 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.5843. Min Act: -0.1700
Data Index: 2093894 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.5843. Min Act: -0.1700
Data Index: 5015223 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.5843. Min Act: -0.1700
Data Index: 4725428 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9593. Min Range: -4.9593
Max Act: 4.5843. Min Act: -0.1700
Data Index: 3006647 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19