Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4156 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.2718. Min Act: -0.1700
Data Index: 6453255 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.2718. Min Act: -0.1700
Data Index: 1495213 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.2718. Min Act: -0.1700
Data Index: 7503501 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.2406. Min Act: -0.1700
Data Index: 8504039 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.2406. Min Act: -0.1700
Data Index: 1495199 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.2093. Min Act: -0.1700
Data Index: 4349455 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1781. Min Act: -0.1700
Data Index: 4349451 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1781. Min Act: -0.1700
Data Index: 6995949 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1781. Min Act: -0.1700
Data Index: 5067110 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1781. Min Act: -0.1700
Data Index: 4349445 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1468. Min Act: -0.1700
Data Index: 6626317 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1468. Min Act: -0.1700
Data Index: 6281265 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1468. Min Act: -0.1700
Data Index: 3301586 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1468. Min Act: -0.1700
Data Index: 8504034 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1468. Min Act: -0.1700
Data Index: 4349441 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1156. Min Act: -0.1700
Data Index: 8504036 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1468. Min Act: -0.1700
Data Index: 311742 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1468. Min Act: -0.1700
Data Index: 5704798 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1156. Min Act: -0.1700
Data Index: 2731410 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2718. Min Range: -5.2718
Max Act: 5.1156. Min Act: -0.1700
Data Index: 3346641 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19