Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7877. Min Range: -8.7877
Max Act: 8.7877. Min Act: -0.1700
Data Index: 7914404 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7877. Min Range: -8.7877
Max Act: 8.6002. Min Act: -0.1700
Data Index: 2229563 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7877. Min Range: -8.7877
Max Act: 8.1627. Min Act: -0.1700
Data Index: 1790603 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7877. Min Range: -8.7877
Max Act: 8.0377. Min Act: -0.1700
Data Index: 1983347 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7877. Min Range: -8.7877
Max Act: 8.0377. Min Act: -0.1700
Data Index: 7940538 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.9752. Min Act: -0.1700
Data Index: 232753 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.9127. Min Act: -0.1700
Data Index: 508258 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.9752. Min Act: -0.1700
Data Index: 5022400 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.9127. Min Act: -0.1700
Data Index: 5602027 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.8502. Min Act: -0.1700
Data Index: 3897479 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.8502. Min Act: -0.1700
Data Index: 901065 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.8502. Min Act: -0.1700
Data Index: 564251 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.8502. Min Act: -0.1700
Data Index: 866258 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.7877. Min Act: -0.1700
Data Index: 4415434 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.7252. Min Act: -0.1700
Data Index: 5885958 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.7877. Min Act: -0.1700
Data Index: 3143665 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.7252. Min Act: -0.1700
Data Index: 669994 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.7252. Min Act: -0.1700
Data Index: 3896102 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.6627. Min Act: -0.1700
Data Index: 6785620 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7877. Min Range: -8.7877
Max Act: 7.6627. Min Act: -0.1700
Data Index: 8679595 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19