Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1600 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.9607. Min Act: -0.1698
Data Index: 1637735 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.9295. Min Act: -0.1700
Data Index: 6115642 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.8982. Min Act: -0.1700
Data Index: 5866092 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.8670. Min Act: -0.1700
Data Index: 2386771 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.8357. Min Act: -0.1700
Data Index: 422197 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7732. Min Act: -0.1700
Data Index: 7482640 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.8045. Min Act: -0.1700
Data Index: 7140898 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7732. Min Act: -0.1700
Data Index: 4279329 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1700
Data Index: 3970058 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7732. Min Act: -0.1700
Data Index: 3198707 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7732. Min Act: -0.1700
Data Index: 3719329 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1697
Data Index: 173968 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1699
Data Index: 4017756 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1681
Data Index: 7070608 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1700
Data Index: 2170750 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1700
Data Index: 6853399 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1700
Data Index: 4962972 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1700
Data Index: 2135890 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1700
Data Index: 6356772 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9607. Min Range: -4.9607
Max Act: 4.7420. Min Act: -0.1700
Data Index: 2013122 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19