Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.5318. Min Act: -0.1700
Data Index: 649817 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.5005. Min Act: -0.1700
Data Index: 5986324 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.4693. Min Act: -0.1700
Data Index: 2435078 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.4380. Min Act: -0.1700
Data Index: 7557777 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.4380. Min Act: -0.1700
Data Index: 3998825 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.4068. Min Act: -0.1700
Data Index: 1518769 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.3755. Min Act: -0.1700
Data Index: 6464937 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.4068. Min Act: -0.1700
Data Index: 1110127 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.3443. Min Act: -0.1700
Data Index: 4441956 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2505. Min Act: -0.1700
Data Index: 8715712 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2505. Min Act: -0.1700
Data Index: 5278678 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2505. Min Act: -0.1700
Data Index: 6125686 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2818. Min Act: -0.1700
Data Index: 8306490 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7383233 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2505. Min Act: -0.1700
Data Index: 4230636 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.1880. Min Act: -0.1700
Data Index: 4910583 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2193. Min Act: -0.1700
Data Index: 5426102 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.1880. Min Act: -0.1700
Data Index: 5206434 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2193. Min Act: -0.1700
Data Index: 6379117 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5318. Min Range: -5.5318
Max Act: 5.2193. Min Act: -0.1700
Data Index: 8499778 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19