Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2251 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6984. Min Act: -0.1700
Data Index: 2147852 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 3066460 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 2135343 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6358. Min Act: -0.1700
Data Index: 4564367 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 3534081 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 5062964 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.6045. Min Act: -0.1700
Data Index: 3392605 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5732. Min Act: -0.1700
Data Index: 4121059 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5732. Min Act: -0.1700
Data Index: 219569 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5732. Min Act: -0.1700
Data Index: 6630372 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5732. Min Act: -0.1700
Data Index: 2713227 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5732. Min Act: -0.1700
Data Index: 2800083 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5419. Min Act: -0.1700
Data Index: 1856516 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5419. Min Act: -0.1700
Data Index: 4467467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5419. Min Act: -0.1700
Data Index: 4750766 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5419. Min Act: -0.1700
Data Index: 4138227 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5419. Min Act: -0.1700
Data Index: 728119 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5419. Min Act: -0.1700
Data Index: 6936841 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5419. Min Act: -0.1700
Data Index: 8749843 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6984. Min Range: -3.6984
Max Act: 3.5419. Min Act: -0.1700
Data Index: 1723968 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19