Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4594 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.8581. Min Act: -0.1700
Data Index: 8068200 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.8581. Min Act: -0.1700
Data Index: 4774440 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.7643. Min Act: -0.1700
Data Index: 4176841 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.7331. Min Act: -0.1700
Data Index: 3745535 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.7331. Min Act: -0.1700
Data Index: 4579967 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6706. Min Act: -0.1700
Data Index: 7445454 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6706. Min Act: -0.1700
Data Index: 4816090 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.7018. Min Act: -0.1700
Data Index: 2156197 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6706. Min Act: -0.1700
Data Index: 8258942 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6081. Min Act: -0.1700
Data Index: 1048771 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6706. Min Act: -0.1700
Data Index: 3733847 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6393. Min Act: -0.1700
Data Index: 8717861 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6393. Min Act: -0.1700
Data Index: 5464943 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.5768. Min Act: -0.1700
Data Index: 6947050 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6081. Min Act: -0.1700
Data Index: 6648642 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6081. Min Act: -0.1700
Data Index: 3855280 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.6081. Min Act: -0.1700
Data Index: 8260977 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.5768. Min Act: -0.1700
Data Index: 3657774 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.5768. Min Act: -0.1700
Data Index: 4461007 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8581. Min Range: -4.8581
Max Act: 4.5456. Min Act: -0.1700
Data Index: 490971 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19