Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.6807. Min Act: -0.1700
Data Index: 5726151 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.6807. Min Act: -0.1700
Data Index: 1339042 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.6182. Min Act: -0.1700
Data Index: 6348540 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.6182. Min Act: -0.1700
Data Index: 4415218 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.6182. Min Act: -0.1700
Data Index: 2921294 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.6182. Min Act: -0.1700
Data Index: 513212 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5869. Min Act: -0.1700
Data Index: 6254009 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5869. Min Act: -0.1700
Data Index: 3336312 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5557. Min Act: -0.1700
Data Index: 8490729 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5557. Min Act: -0.1700
Data Index: 7967713 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5557. Min Act: -0.1700
Data Index: 1399126 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5557. Min Act: -0.1700
Data Index: 687510 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5557. Min Act: -0.1700
Data Index: 1156327 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5557. Min Act: -0.1700
Data Index: 1254682 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5244. Min Act: -0.1700
Data Index: 7852371 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5244. Min Act: -0.1700
Data Index: 5001379 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5244. Min Act: -0.1700
Data Index: 5100970 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5244. Min Act: -0.1700
Data Index: 2670561 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.5244. Min Act: -0.1700
Data Index: 687512 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6807. Min Range: -4.6807
Max Act: 4.4932. Min Act: -0.1700
Data Index: 4835431 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19