Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4803 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.7851. Min Act: -0.1700
Data Index: 3130076 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6914. Min Act: -0.1700
Data Index: 7350145 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6914. Min Act: -0.1700
Data Index: 5573259 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6914. Min Act: -0.1700
Data Index: 5048330 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6914. Min Act: -0.1700
Data Index: 2423104 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6601. Min Act: -0.1700
Data Index: 1581757 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6601. Min Act: -0.1700
Data Index: 7495185 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6601. Min Act: -0.1700
Data Index: 7175648 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6601. Min Act: -0.1700
Data Index: 5573261 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6601. Min Act: -0.1700
Data Index: 3472162 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6601. Min Act: -0.1700
Data Index: 5705428 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6289. Min Act: -0.1700
Data Index: 805163 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6289. Min Act: -0.1700
Data Index: 2277898 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.5976. Min Act: -0.1700
Data Index: 4560348 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6289. Min Act: -0.1700
Data Index: 388202 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6289. Min Act: -0.1700
Data Index: 2631274 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6289. Min Act: -0.1700
Data Index: 5728638 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6289. Min Act: -0.1700
Data Index: 6122499 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6289. Min Act: -0.1700
Data Index: 40794 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7851. Min Range: -4.7851
Max Act: 4.6289. Min Act: -0.1700
Data Index: 2071127 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19