Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5721 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.7095. Min Act: -0.1700
Data Index: 3817709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.6400. Min Act: -0.1700
Data Index: 6334114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.6400. Min Act: -0.1700
Data Index: 3689480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.6051. Min Act: -0.1700
Data Index: 5751327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.6051. Min Act: -0.1700
Data Index: 4963881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.6051. Min Act: -0.1700
Data Index: 3999191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5702. Min Act: -0.1700
Data Index: 5254007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5702. Min Act: -0.1700
Data Index: 5069766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5527. Min Act: -0.1700
Data Index: 8485986 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5527. Min Act: -0.1700
Data Index: 6493558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5527. Min Act: -0.1700
Data Index: 1874273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5527. Min Act: -0.1700
Data Index: 1507969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5351. Min Act: -0.1700
Data Index: 5207160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5351. Min Act: -0.1700
Data Index: 1697216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5176. Min Act: -0.1700
Data Index: 4386015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5176. Min Act: -0.1700
Data Index: 8612161 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5176. Min Act: -0.1700
Data Index: 349837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5176. Min Act: -0.1700
Data Index: 7449602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5001. Min Act: -0.1700
Data Index: 5199437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7095. Min Range: -1.7095
Max Act: 1.5001. Min Act: -0.1700
Data Index: 3147517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19