Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1342 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.6615. Min Act: -0.1700
Data Index: 7970009 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.6615. Min Act: -0.1700
Data Index: 4542341 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5918. Min Act: -0.1700
Data Index: 7062395 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 2219799 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 2198103 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 2153920 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 1832554 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 2307921 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 2050175 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 2011586 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 750137 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 1133623 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 2273591 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 1562396 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 1987230 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 694552 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 231081 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 2630874 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 1098485 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6615. Min Range: -1.6615
Max Act: 1.5743. Min Act: -0.1700
Data Index: 1588182 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19