Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.6708. Min Act: -0.1700
Data Index: 4817268 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.5146. Min Act: -0.1700
Data Index: 1548417 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.4521. Min Act: -0.1700
Data Index: 5039751 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.3896. Min Act: -0.1700
Data Index: 6146960 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.2333. Min Act: -0.1700
Data Index: 2336741 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.2333. Min Act: -0.1700
Data Index: 757888 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.2333. Min Act: -0.1700
Data Index: 1158177 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.2021. Min Act: -0.1700
Data Index: 887400 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.2021. Min Act: -0.1700
Data Index: 6890160 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.0771. Min Act: -0.1700
Data Index: 6513645 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.0771. Min Act: -0.1700
Data Index: 8734295 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.1083. Min Act: -0.1700
Data Index: 7653970 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6708. Min Range: -7.6708
Max Act: 7.0146. Min Act: -0.1700
Data Index: 7299297 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6708. Min Range: -7.6708
Max Act: 6.9521. Min Act: -0.1700
Data Index: 1414510 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6708. Min Range: -7.6708
Max Act: 6.9521. Min Act: -0.1700
Data Index: 2902821 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6708. Min Range: -7.6708
Max Act: 6.9208. Min Act: -0.1700
Data Index: 5157273 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6708. Min Range: -7.6708
Max Act: 6.9208. Min Act: -0.1700
Data Index: 3685265 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6708. Min Range: -7.6708
Max Act: 6.9208. Min Act: -0.1700
Data Index: 3219129 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6708. Min Range: -7.6708
Max Act: 6.9208. Min Act: -0.1700
Data Index: 1548648 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6708. Min Range: -7.6708
Max Act: 6.8896. Min Act: -0.1700
Data Index: 5805080 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19