Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4945. Min Range: -9.4945
Max Act: 9.4945. Min Act: -0.1700
Data Index: 3197234 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4945. Min Range: -9.4945
Max Act: 9.4320. Min Act: -0.1700
Data Index: 4061011 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4945. Min Range: -9.4945
Max Act: 9.4320. Min Act: -0.1700
Data Index: 6597721 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4945. Min Range: -9.4945
Max Act: 9.3695. Min Act: -0.1700
Data Index: 4550301 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4945. Min Range: -9.4945
Max Act: 9.3695. Min Act: -0.1700
Data Index: 3340657 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4945. Min Range: -9.4945
Max Act: 9.0570. Min Act: -0.1700
Data Index: 2497388 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.9945. Min Act: -0.1700
Data Index: 6183882 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.8695. Min Act: -0.1700
Data Index: 889369 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.8695. Min Act: -0.1700
Data Index: 5320427 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.8070. Min Act: -0.1700
Data Index: 15351 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.7445. Min Act: -0.1700
Data Index: 7940447 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.7445. Min Act: -0.1700
Data Index: 8209550 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.7445. Min Act: -0.1700
Data Index: 5942404 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.6820. Min Act: -0.1699
Data Index: 827561 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.6820. Min Act: -0.1700
Data Index: 4039517 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.6820. Min Act: -0.1700
Data Index: 4708701 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.6820. Min Act: -0.1700
Data Index: 5481938 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.6195. Min Act: -0.1700
Data Index: 773804 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.6820. Min Act: -0.1700
Data Index: 1837632 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4945. Min Range: -9.4945
Max Act: 8.4945. Min Act: -0.1700
Data Index: 3915246 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19