Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7032. Min Range: -7.7032
Max Act: 7.7032. Min Act: -0.1700
Data Index: 5113904 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7032. Min Range: -7.7032
Max Act: 7.2344. Min Act: -0.1700
Data Index: 7661791 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7032. Min Range: -7.7032
Max Act: 7.0157. Min Act: -0.1700
Data Index: 1934241 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8907. Min Act: -0.1700
Data Index: 5154375 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.9219. Min Act: -0.1700
Data Index: 40097 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.9219. Min Act: -0.1700
Data Index: 2795700 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.9219. Min Act: -0.1700
Data Index: 736577 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.9219. Min Act: -0.1700
Data Index: 2795689 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8907. Min Act: -0.1700
Data Index: 1631649 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8907. Min Act: -0.1700
Data Index: 7798202 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8594. Min Act: -0.1700
Data Index: 745563 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8594. Min Act: -0.1700
Data Index: 8763093 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8282. Min Act: -0.1700
Data Index: 8701363 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8594. Min Act: -0.1700
Data Index: 8484458 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8282. Min Act: -0.1700
Data Index: 2883661 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8594. Min Act: -0.1700
Data Index: 3488604 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.8282. Min Act: -0.1700
Data Index: 5961376 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.7969. Min Act: -0.1700
Data Index: 783588 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.7657. Min Act: -0.1700
Data Index: 4954491 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7032. Min Range: -7.7032
Max Act: 6.7969. Min Act: -0.1700
Data Index: 4993887 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19