Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4212 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2016. Min Range: -7.2016
Max Act: 7.2016. Min Act: -0.1700
Data Index: 6396337 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2016. Min Range: -7.2016
Max Act: 7.1391. Min Act: -0.1700
Data Index: 250149 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2016. Min Range: -7.2016
Max Act: 7.1078. Min Act: -0.1700
Data Index: 2043415 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2016. Min Range: -7.2016
Max Act: 7.0766. Min Act: -0.1700
Data Index: 2773497 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2016. Min Range: -7.2016
Max Act: 7.0453. Min Act: -0.1700
Data Index: 6537702 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.8891. Min Act: -0.1700
Data Index: 451105 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.8578. Min Act: -0.1700
Data Index: 3540169 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.8266. Min Act: -0.1700
Data Index: 8032166 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.7953. Min Act: -0.1700
Data Index: 2946791 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.7953. Min Act: -0.1700
Data Index: 56816 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.7641. Min Act: -0.1700
Data Index: 5709383 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.7641. Min Act: -0.1700
Data Index: 2125490 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.6703. Min Act: -0.1700
Data Index: 2143762 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.6703. Min Act: -0.1700
Data Index: 2767899 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.6391. Min Act: -0.1700
Data Index: 4222621 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.7016. Min Act: -0.1700
Data Index: 618333 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.6391. Min Act: -0.1700
Data Index: 6541290 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.6391. Min Act: -0.1700
Data Index: 8375623 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.6391. Min Act: -0.1700
Data Index: 7911590 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2016. Min Range: -7.2016
Max Act: 6.6078. Min Act: -0.1700
Data Index: 4024130 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19