Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.4012. Min Act: -0.1700
Data Index: 5356266 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1824. Min Act: -0.1700
Data Index: 8529791 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.1199. Min Act: -0.1700
Data Index: 3017268 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4012. Min Range: -5.4012
Max Act: 5.0887. Min Act: -0.1700
Data Index: 1795428 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.9324. Min Act: -0.1700
Data Index: 860771 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.9324. Min Act: -0.1700
Data Index: 6867085 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.9012. Min Act: -0.1700
Data Index: 8800711 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.9012. Min Act: -0.1700
Data Index: 5152916 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8699. Min Act: -0.1700
Data Index: 2552865 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.9012. Min Act: -0.1700
Data Index: 826124 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8699. Min Act: -0.1700
Data Index: 2385277 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8387. Min Act: -0.1700
Data Index: 5535801 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8387. Min Act: -0.1700
Data Index: 7174670 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8387. Min Act: -0.1700
Data Index: 5740493 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8387. Min Act: -0.1700
Data Index: 7946876 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8387. Min Act: -0.1700
Data Index: 860773 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8074. Min Act: -0.1700
Data Index: 1788247 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8074. Min Act: -0.1700
Data Index: 860772 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8387. Min Act: -0.1700
Data Index: 3406525 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4012. Min Range: -5.4012
Max Act: 4.8074. Min Act: -0.1700
Data Index: 1419884 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19