Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4265 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0708. Min Range: -6.0708
Max Act: 6.0708. Min Act: -0.1700
Data Index: 4346032 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.9771. Min Act: -0.1700
Data Index: 25794 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.9146. Min Act: -0.1700
Data Index: 1279055 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.8833. Min Act: -0.1700
Data Index: 8827115 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.8833. Min Act: -0.1700
Data Index: 68403 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.8521. Min Act: -0.1700
Data Index: 612802 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.7896. Min Act: -0.1700
Data Index: 3536607 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.8208. Min Act: -0.1700
Data Index: 5895944 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.8208. Min Act: -0.1700
Data Index: 6846812 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.7896. Min Act: -0.1700
Data Index: 4212267 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.7896. Min Act: -0.1700
Data Index: 1285131 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.7896. Min Act: -0.1700
Data Index: 5888437 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.7583. Min Act: -0.1700
Data Index: 3143354 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.7583. Min Act: -0.1700
Data Index: 5178102 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.6646. Min Act: -0.1700
Data Index: 5017015 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.6958. Min Act: -0.1700
Data Index: 885223 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.6958. Min Act: -0.1700
Data Index: 4604552 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.6646. Min Act: -0.1700
Data Index: 3748801 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.6646. Min Act: -0.1700
Data Index: 3323671 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0708. Min Range: -6.0708
Max Act: 5.6646. Min Act: -0.1700
Data Index: 7075407 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19