Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2869. Min Range: -5.2869
Max Act: 5.2869. Min Act: -0.1700
Data Index: 1961134 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2869. Min Range: -5.2869
Max Act: 5.0994. Min Act: -0.1700
Data Index: 103055 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2869. Min Range: -5.2869
Max Act: 5.0057. Min Act: -0.1700
Data Index: 1265773 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2869. Min Range: -5.2869
Max Act: 5.0369. Min Act: -0.1700
Data Index: 8650299 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.9744. Min Act: -0.1700
Data Index: 8650293 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2869. Min Range: -5.2869
Max Act: 5.0057. Min Act: -0.1700
Data Index: 8650295 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2869. Min Range: -5.2869
Max Act: 5.0057. Min Act: -0.1700
Data Index: 730469 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.9432. Min Act: -0.1700
Data Index: 6605595 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3603527 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.9119. Min Act: -0.1700
Data Index: 8650289 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.9119. Min Act: -0.1700
Data Index: 8650291 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.9119. Min Act: -0.1700
Data Index: 4736963 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.9119. Min Act: -0.1700
Data Index: 7057119 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.9119. Min Act: -0.1700
Data Index: 503144 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.8807. Min Act: -0.1700
Data Index: 8650290 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.8807. Min Act: -0.1700
Data Index: 7678466 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.8807. Min Act: -0.1700
Data Index: 8650298 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.8807. Min Act: -0.1700
Data Index: 8650297 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.8807. Min Act: -0.1700
Data Index: 4577142 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2869. Min Range: -5.2869
Max Act: 4.8807. Min Act: -0.1700
Data Index: 8641998 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19