Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 872 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.5860. Min Act: -0.1700
Data Index: 1757020 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.3047. Min Act: -0.1700
Data Index: 5800404 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.2422. Min Act: -0.1700
Data Index: 831585 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1797. Min Act: -0.1700
Data Index: 6525687 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1797. Min Act: -0.1700
Data Index: 1929653 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1797. Min Act: -0.1700
Data Index: 536647 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1797. Min Act: -0.1700
Data Index: 6387365 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1697
Data Index: 7798721 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 2956741 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1485. Min Act: -0.1700
Data Index: 4625099 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1485. Min Act: -0.1700
Data Index: 584358 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 527754 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 6161045 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 3517708 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 6065996 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 956934 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.0860. Min Act: -0.1700
Data Index: 3576705 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.0860. Min Act: -0.1700
Data Index: 4236922 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.0860. Min Act: -0.1700
Data Index: 536494 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.0860. Min Act: -0.1700
Data Index: 5293474 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19