Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1081 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.2926. Min Act: -0.1700
Data Index: 4562359 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.2614. Min Act: -0.1700
Data Index: 6365766 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.1364. Min Act: -0.1700
Data Index: 8145115 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.1364. Min Act: -0.1700
Data Index: 1528962 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.0739. Min Act: -0.1700
Data Index: 2627292 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.0739. Min Act: -0.1700
Data Index: 614409 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.0426. Min Act: -0.1700
Data Index: 2062146 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.0426. Min Act: -0.1700
Data Index: 2388130 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2926. Min Range: -7.2926
Max Act: 7.0426. Min Act: -0.1700
Data Index: 7351371 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.9489. Min Act: -0.1700
Data Index: 316838 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.9801. Min Act: -0.1700
Data Index: 2702041 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.9489. Min Act: -0.1700
Data Index: 5565340 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.9176. Min Act: -0.1700
Data Index: 6131721 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.8864. Min Act: -0.1700
Data Index: 1430199 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.8864. Min Act: -0.1700
Data Index: 8549068 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.8864. Min Act: -0.1700
Data Index: 3860320 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.8551. Min Act: -0.1700
Data Index: 1935435 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.8551. Min Act: -0.1700
Data Index: 6220026 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.8551. Min Act: -0.1700
Data Index: 6319523 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2926. Min Range: -7.2926
Max Act: 6.8864. Min Act: -0.1700
Data Index: 5718938 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19