Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4176 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1413. Min Range: -6.1413
Max Act: 6.1413. Min Act: -0.1700
Data Index: 5946637 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1413. Min Range: -6.1413
Max Act: 6.1100. Min Act: -0.1700
Data Index: 8462158 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1413. Min Range: -6.1413
Max Act: 6.0788. Min Act: -0.1700
Data Index: 1333624 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.9850. Min Act: -0.1700
Data Index: 1571083 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.9850. Min Act: -0.1700
Data Index: 1008772 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.8288. Min Act: -0.1700
Data Index: 3019714 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.8288. Min Act: -0.1700
Data Index: 8393001 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.7975. Min Act: -0.1700
Data Index: 1166902 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.7350. Min Act: -0.1700
Data Index: 4737133 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.7350. Min Act: -0.1700
Data Index: 1476634 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.7038. Min Act: -0.1700
Data Index: 7644553 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6725. Min Act: -0.1700
Data Index: 2967292 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6725. Min Act: -0.1700
Data Index: 3255530 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6413. Min Act: -0.1700
Data Index: 4738487 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6725. Min Act: -0.1700
Data Index: 4817153 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6413. Min Act: -0.1700
Data Index: 2198804 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6413. Min Act: -0.1700
Data Index: 2955376 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6100. Min Act: -0.1700
Data Index: 7987550 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6100. Min Act: -0.1700
Data Index: 5900135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1413. Min Range: -6.1413
Max Act: 5.6413. Min Act: -0.1699
Data Index: 3114896 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19