Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.6201. Min Act: -0.1700
Data Index: 621446 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.6201. Min Act: -0.1700
Data Index: 4727832 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.6201. Min Act: -0.1700
Data Index: 6881033 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5718. Min Act: -0.1700
Data Index: 5232737 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5879. Min Act: -0.1700
Data Index: 455130 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5879. Min Act: -0.1700
Data Index: 5672589 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5879. Min Act: -0.1700
Data Index: 6774854 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5718. Min Act: -0.1700
Data Index: 7407918 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5556. Min Act: -0.1700
Data Index: 7871068 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5718. Min Act: -0.1700
Data Index: 2759954 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5718. Min Act: -0.1700
Data Index: 4435133 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5718. Min Act: -0.1700
Data Index: 3106998 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5718. Min Act: -0.1700
Data Index: 121287 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5556. Min Act: -0.1700
Data Index: 1622015 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5718. Min Act: -0.1700
Data Index: 7516234 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5556. Min Act: -0.1700
Data Index: 2452039 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5395. Min Act: -0.1700
Data Index: 6275119 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5556. Min Act: -0.1700
Data Index: 5233528 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5556. Min Act: -0.1700
Data Index: 5845808 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6201. Min Range: -2.6201
Max Act: 2.5395. Min Act: -0.1700
Data Index: 5903435 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19