Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0742. Min Range: -8.0742
Max Act: 8.0742. Min Act: -0.1700
Data Index: 8381723 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0742. Min Range: -8.0742
Max Act: 8.0742. Min Act: -0.1700
Data Index: 2489970 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.4180. Min Act: -0.1700
Data Index: 2974709 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.3867. Min Act: -0.1700
Data Index: 4831088 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.3555. Min Act: -0.1700
Data Index: 6445186 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.3242. Min Act: -0.1700
Data Index: 7725988 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.2617. Min Act: -0.1700
Data Index: 7832345 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.1992. Min Act: -0.1700
Data Index: 4611566 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.1367. Min Act: -0.1700
Data Index: 7971993 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.1367. Min Act: -0.1700
Data Index: 5202951 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.0430. Min Act: -0.1700
Data Index: 769731 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.0430. Min Act: -0.1700
Data Index: 1262331 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.0742. Min Act: -0.1700
Data Index: 3386902 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0742. Min Range: -8.0742
Max Act: 7.0742. Min Act: -0.1700
Data Index: 4254353 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0742. Min Range: -8.0742
Max Act: 6.9492. Min Act: -0.1700
Data Index: 5434902 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0742. Min Range: -8.0742
Max Act: 6.8867. Min Act: -0.1700
Data Index: 2700383 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0742. Min Range: -8.0742
Max Act: 6.8867. Min Act: -0.1700
Data Index: 3455552 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0742. Min Range: -8.0742
Max Act: 6.8867. Min Act: -0.1700
Data Index: 33838 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0742. Min Range: -8.0742
Max Act: 6.8867. Min Act: -0.1700
Data Index: 2333569 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0742. Min Range: -8.0742
Max Act: 6.8867. Min Act: -0.1700
Data Index: 8072594 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19