Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8452. Min Act: -0.1700
Data Index: 6696529 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8452. Min Act: -0.1700
Data Index: 2952131 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8452. Min Act: -0.1700
Data Index: 5552204 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8281. Min Act: -0.1700
Data Index: 7126038 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8281. Min Act: -0.1700
Data Index: 1010258 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8281. Min Act: -0.1700
Data Index: 4960456 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8281. Min Act: -0.1700
Data Index: 4354809 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8109. Min Act: -0.1700
Data Index: 8226877 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8109. Min Act: -0.1700
Data Index: 8637679 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7937. Min Act: -0.1700
Data Index: 1487009 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7937. Min Act: -0.1700
Data Index: 3138445 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7937. Min Act: -0.1700
Data Index: 1810770 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7937. Min Act: -0.1700
Data Index: 4766516 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7937. Min Act: -0.1700
Data Index: 369913 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7937. Min Act: -0.1700
Data Index: 8372608 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7937. Min Act: -0.1700
Data Index: 3581108 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7765. Min Act: -0.1700
Data Index: 6949714 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7765. Min Act: -0.1700
Data Index: 3626223 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7765. Min Act: -0.1700
Data Index: 823436 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.7765. Min Act: -0.1700
Data Index: 5324257 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19