Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3969 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2682. Min Range: -7.2682
Max Act: 7.2682. Min Act: -0.1700
Data Index: 8627497 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2682. Min Range: -7.2682
Max Act: 7.0182. Min Act: -0.1700
Data Index: 8285049 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.9869. Min Act: -0.1700
Data Index: 6561021 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.7994. Min Act: -0.1700
Data Index: 7162588 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.8307. Min Act: -0.1700
Data Index: 7772673 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.7682. Min Act: -0.1700
Data Index: 7806833 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.7682. Min Act: -0.1700
Data Index: 1625320 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.6744. Min Act: -0.1700
Data Index: 2760601 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.6744. Min Act: -0.1700
Data Index: 1521881 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.6119. Min Act: -0.1700
Data Index: 7564356 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.5807. Min Act: -0.1700
Data Index: 4286765 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.5807. Min Act: -0.1700
Data Index: 7140291 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.5494. Min Act: -0.1700
Data Index: 775969 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.5182. Min Act: -0.1700
Data Index: 1757303 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.5182. Min Act: -0.1700
Data Index: 6745086 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.5182. Min Act: -0.1700
Data Index: 2634770 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.4869. Min Act: -0.1700
Data Index: 7501211 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.4869. Min Act: -0.1700
Data Index: 5258441 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.4244. Min Act: -0.1700
Data Index: 5927108 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2682. Min Range: -7.2682
Max Act: 6.4244. Min Act: -0.1700
Data Index: 3455473 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19