Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.3582. Min Act: -0.1700
Data Index: 515895 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1707. Min Act: -0.1700
Data Index: 7966262 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1707. Min Act: -0.1700
Data Index: 263229 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1082. Min Act: -0.1700
Data Index: 5180131 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1082. Min Act: -0.1700
Data Index: 4907296 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1082. Min Act: -0.1700
Data Index: 3370405 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.0770. Min Act: -0.1700
Data Index: 488407 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1082. Min Act: -0.1700
Data Index: 2850367 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1082. Min Act: -0.1700
Data Index: 5678783 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1082. Min Act: -0.1700
Data Index: 2615793 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1082. Min Act: -0.1700
Data Index: 2110601 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.0457. Min Act: -0.1700
Data Index: 3204629 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.1082. Min Act: -0.1700
Data Index: 2992293 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.0770. Min Act: -0.1700
Data Index: 2794755 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.0770. Min Act: -0.1700
Data Index: 1375040 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.0145. Min Act: -0.1700
Data Index: 5757152 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.0145. Min Act: -0.1700
Data Index: 5225680 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.0145. Min Act: -0.1700
Data Index: 5225662 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3582. Min Range: -5.3582
Max Act: 5.0457. Min Act: -0.1700
Data Index: 5225692 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3582. Min Range: -5.3582
Max Act: 4.9832. Min Act: -0.1700
Data Index: 3711088 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19