Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4984. Min Range: -7.4984
Max Act: 7.4984. Min Act: -0.1700
Data Index: 2855913 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4984. Min Range: -7.4984
Max Act: 7.3421. Min Act: -0.1700
Data Index: 6168054 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4984. Min Range: -7.4984
Max Act: 7.2171. Min Act: -0.1700
Data Index: 5481654 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4984. Min Range: -7.4984
Max Act: 7.1234. Min Act: -0.1700
Data Index: 4264602 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4984. Min Range: -7.4984
Max Act: 7.0609. Min Act: -0.1700
Data Index: 1000983 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4984. Min Range: -7.4984
Max Act: 7.0296. Min Act: -0.1700
Data Index: 6880808 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9984. Min Act: -0.1700
Data Index: 8726774 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4984. Min Range: -7.4984
Max Act: 7.0296. Min Act: -0.1700
Data Index: 101917 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4984. Min Range: -7.4984
Max Act: 7.0296. Min Act: -0.1700
Data Index: 3422912 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9984. Min Act: -0.1700
Data Index: 3860443 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9671. Min Act: -0.1700
Data Index: 4990883 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9671. Min Act: -0.1700
Data Index: 377750 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9046. Min Act: -0.1700
Data Index: 3495121 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9359. Min Act: -0.1700
Data Index: 3406323 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9046. Min Act: -0.1700
Data Index: 6802632 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9046. Min Act: -0.1700
Data Index: 6567513 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9046. Min Act: -0.1700
Data Index: 8815397 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.8734. Min Act: -0.1700
Data Index: 4977768 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.9359. Min Act: -0.1700
Data Index: 4475142 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4984. Min Range: -7.4984
Max Act: 6.8734. Min Act: -0.1700
Data Index: 4663934 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19