Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2567 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.5996. Min Act: -0.1700
Data Index: 8452048 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.5370. Min Act: -0.1700
Data Index: 4128208 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.5056. Min Act: -0.1700
Data Index: 472560 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4743. Min Act: -0.1700
Data Index: 1752260 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4743. Min Act: -0.1700
Data Index: 8623697 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4743. Min Act: -0.1700
Data Index: 805919 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4743. Min Act: -0.1700
Data Index: 6923584 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4743. Min Act: -0.1700
Data Index: 8041585 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4430. Min Act: -0.1700
Data Index: 6321123 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4430. Min Act: -0.1700
Data Index: 3474904 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4430. Min Act: -0.1700
Data Index: 8093124 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4430. Min Act: -0.1700
Data Index: 2950678 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4430. Min Act: -0.1700
Data Index: 7097945 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4430. Min Act: -0.1700
Data Index: 2633156 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4430. Min Act: -0.1700
Data Index: 6820083 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4743. Min Act: -0.1700
Data Index: 2141293 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4430. Min Act: -0.1700
Data Index: 254694 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4116. Min Act: -0.1700
Data Index: 4165293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4116. Min Act: -0.1700
Data Index: 4474955 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5996. Min Range: -3.5996
Max Act: 3.4116. Min Act: -0.1700
Data Index: 1642864 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19