Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2797 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0853. Min Range: -7.0853
Max Act: 7.0853. Min Act: -0.1700
Data Index: 666862 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.8040. Min Act: -0.1700
Data Index: 5059111 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.7728. Min Act: -0.1700
Data Index: 192932 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.7728. Min Act: -0.1700
Data Index: 4669463 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.7415. Min Act: -0.1700
Data Index: 1969066 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 902593 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 3769784 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 2733043 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 6015602 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 5171366 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6165. Min Act: -0.1700
Data Index: 7620392 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.5853. Min Act: -0.1700
Data Index: 303967 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.5853. Min Act: -0.1700
Data Index: 1203554 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.5853. Min Act: -0.1700
Data Index: 3589456 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6165. Min Act: -0.1700
Data Index: 8555283 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.5853. Min Act: -0.1700
Data Index: 6748064 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.5853. Min Act: -0.1700
Data Index: 1926792 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.5540. Min Act: -0.1700
Data Index: 3112647 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.5540. Min Act: -0.1700
Data Index: 6559821 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.5228. Min Act: -0.1700
Data Index: 1385428 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19