Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2440 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.6541. Min Act: -0.1700
Data Index: 7395817 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.3416. Min Act: -0.1700
Data Index: 1543300 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.2791. Min Act: -0.1700
Data Index: 1705731 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.2166. Min Act: -0.1700
Data Index: 4563491 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.1853. Min Act: -0.1700
Data Index: 4423604 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.1853. Min Act: -0.1700
Data Index: 8659698 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.1853. Min Act: -0.1700
Data Index: 3212288 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.0603. Min Act: -0.1700
Data Index: 7905848 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6541. Min Range: -6.6541
Max Act: 6.0916. Min Act: -0.1700
Data Index: 4982851 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9978. Min Act: -0.1700
Data Index: 479512 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9978. Min Act: -0.1700
Data Index: 7953386 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9666. Min Act: -0.1700
Data Index: 1997830 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9353. Min Act: -0.1700
Data Index: 2675015 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9353. Min Act: -0.1700
Data Index: 4867710 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9353. Min Act: -0.1700
Data Index: 3780109 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9353. Min Act: -0.1700
Data Index: 4600118 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9041. Min Act: -0.1700
Data Index: 7962815 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9041. Min Act: -0.1700
Data Index: 5874602 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9041. Min Act: -0.1700
Data Index: 5680382 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6541. Min Range: -6.6541
Max Act: 5.9041. Min Act: -0.1700
Data Index: 2851009 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19