Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 106 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.7147. Min Act: -0.1700
Data Index: 7971461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.7147. Min Act: -0.1700
Data Index: 1909627 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 1828570 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 5564418 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 1436730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 2726435 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 8599794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 582013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 8552842 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 3613003 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6209. Min Act: -0.1700
Data Index: 45645 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6209. Min Act: -0.1700
Data Index: 4874952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 703053 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 1220613 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 4792045 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 2798275 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 4873775 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 922504 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 4937121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 3479888 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19