Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 983 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.9878. Min Act: -0.1700
Data Index: 2007512 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.9253. Min Act: -0.1700
Data Index: 8091039 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8628. Min Act: -0.1700
Data Index: 3986645 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8315. Min Act: -0.1700
Data Index: 2871599 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8315. Min Act: -0.1700
Data Index: 961197 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8315. Min Act: -0.1700
Data Index: 7807876 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8315. Min Act: -0.1700
Data Index: 184892 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8315. Min Act: -0.1700
Data Index: 2384716 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8315. Min Act: -0.1700
Data Index: 1216875 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8315. Min Act: -0.1700
Data Index: 5852452 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8003. Min Act: -0.1700
Data Index: 4257640 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7690. Min Act: -0.1700
Data Index: 7153302 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7690. Min Act: -0.1700
Data Index: 6170553 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7690. Min Act: -0.1700
Data Index: 2988441 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7690. Min Act: -0.1700
Data Index: 3977146 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8003. Min Act: -0.1700
Data Index: 6424248 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7690. Min Act: -0.1700
Data Index: 4807320 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7690. Min Act: -0.1700
Data Index: 2306234 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7690. Min Act: -0.1700
Data Index: 911199 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7690. Min Act: -0.1700
Data Index: 8350576 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19