Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1590 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0620. Min Range: -5.0620
Max Act: 5.0620. Min Act: -0.1700
Data Index: 2562167 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0620. Min Range: -5.0620
Max Act: 5.0307. Min Act: -0.1700
Data Index: 1992872 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9995. Min Act: -0.1700
Data Index: 4476791 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9995. Min Act: -0.1700
Data Index: 7354523 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9682. Min Act: -0.1700
Data Index: 5897597 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9682. Min Act: -0.1700
Data Index: 8633238 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9682. Min Act: -0.1659
Data Index: 1826124 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9682. Min Act: -0.1700
Data Index: 6966959 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9370. Min Act: -0.1699
Data Index: 2042296 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9370. Min Act: -0.1700
Data Index: 8107941 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9370. Min Act: -0.1700
Data Index: 5964104 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9370. Min Act: -0.1700
Data Index: 3560589 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.9057. Min Act: -0.1700
Data Index: 5413602 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8745. Min Act: -0.1700
Data Index: 8353616 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8745. Min Act: -0.1700
Data Index: 3641222 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8745. Min Act: -0.1700
Data Index: 7340374 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8745. Min Act: -0.1700
Data Index: 5065963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8745. Min Act: -0.1700
Data Index: 6632775 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8745. Min Act: -0.1700
Data Index: 8318601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0620. Min Range: -5.0620
Max Act: 4.8120. Min Act: -0.1693
Data Index: 4293240 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19