Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5361. Min Range: -11.5361
Max Act: 11.5361. Min Act: -0.1700
Data Index: 8068066 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5361. Min Range: -11.5361
Max Act: 11.5361. Min Act: -0.1700
Data Index: 8068071 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5361. Min Range: -11.5361
Max Act: 10.8486. Min Act: -0.1700
Data Index: 888150 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5361. Min Range: -11.5361
Max Act: 10.7236. Min Act: -0.1700
Data Index: 888147 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5361. Min Range: -11.5361
Max Act: 10.0361. Min Act: -0.1700
Data Index: 4025928 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.9736. Min Act: -0.1700
Data Index: 4354849 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.9736. Min Act: -0.1700
Data Index: 8317923 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.9736. Min Act: -0.1700
Data Index: 6975501 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.9111. Min Act: -0.1700
Data Index: 6186049 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.8486. Min Act: -0.1700
Data Index: 491070 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.7861. Min Act: -0.1700
Data Index: 3419964 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.7861. Min Act: -0.1700
Data Index: 6267977 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.7236. Min Act: -0.1700
Data Index: 3978966 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.5986. Min Act: -0.1700
Data Index: 3526515 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.6611. Min Act: -0.1700
Data Index: 1482091 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.5361. Min Act: -0.1700
Data Index: 731199 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.5361. Min Act: -0.1700
Data Index: 7732140 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.4736. Min Act: -0.1700
Data Index: 7257972 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.4736. Min Act: -0.1700
Data Index: 5558939 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5361. Min Range: -11.5361
Max Act: 9.4736. Min Act: -0.1700
Data Index: 5340611 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19