Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5849 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.1040. Min Act: -0.1700
Data Index: 2647040 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0727. Min Act: -0.1700
Data Index: 800527 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0727. Min Act: -0.1700
Data Index: 5700520 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0727. Min Act: -0.1700
Data Index: 5635960 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0415. Min Act: -0.1700
Data Index: 5935137 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0102. Min Act: -0.1700
Data Index: 4737514 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0415. Min Act: -0.1700
Data Index: 3663918 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0102. Min Act: -0.1700
Data Index: 4724404 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0102. Min Act: -0.1700
Data Index: 6113242 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1040. Min Range: -4.1040
Max Act: 4.0102. Min Act: -0.1700
Data Index: 1707484 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9477. Min Act: -0.1700
Data Index: 5919137 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9477. Min Act: -0.1700
Data Index: 4831771 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9477. Min Act: -0.1700
Data Index: 5984679 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9164. Min Act: -0.1700
Data Index: 2657474 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9164. Min Act: -0.1700
Data Index: 685737 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9164. Min Act: -0.1700
Data Index: 3029930 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9164. Min Act: -0.1700
Data Index: 426441 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9164. Min Act: -0.1700
Data Index: 1586444 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9164. Min Act: -0.1700
Data Index: 301009 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1040. Min Range: -4.1040
Max Act: 3.9164. Min Act: -0.1700
Data Index: 3941611 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19