Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7300. Min Range: -9.7300
Max Act: 9.7300. Min Act: -0.1700
Data Index: 3778735 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7300. Min Range: -9.7300
Max Act: 9.4175. Min Act: -0.1700
Data Index: 8353965 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7300. Min Range: -9.7300
Max Act: 9.3550. Min Act: -0.1700
Data Index: 6558728 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7300. Min Range: -9.7300
Max Act: 9.3550. Min Act: -0.1700
Data Index: 406411 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7300. Min Range: -9.7300
Max Act: 9.2925. Min Act: -0.1700
Data Index: 6157940 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7300. Min Range: -9.7300
Max Act: 9.1675. Min Act: -0.1700
Data Index: 5616970 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7300. Min Range: -9.7300
Max Act: 9.0425. Min Act: -0.1700
Data Index: 6753131 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.9800. Min Act: -0.1700
Data Index: 5587768 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7300. Min Range: -9.7300
Max Act: 9.0425. Min Act: -0.1700
Data Index: 6804378 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.9175. Min Act: -0.1700
Data Index: 3778736 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.9175. Min Act: -0.1700
Data Index: 1356763 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.9175. Min Act: -0.1700
Data Index: 2975790 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.9175. Min Act: -0.1700
Data Index: 6276022 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.8550. Min Act: -0.1700
Data Index: 6778930 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.8550. Min Act: -0.1700
Data Index: 3870823 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.8550. Min Act: -0.1700
Data Index: 6371168 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.7925. Min Act: -0.1700
Data Index: 1335184 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.7925. Min Act: -0.1700
Data Index: 6264619 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.7925. Min Act: -0.1700
Data Index: 7494780 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7300. Min Range: -9.7300
Max Act: 8.8550. Min Act: -0.1700
Data Index: 5190649 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19