Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1650 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.5786. Min Act: -0.1700
Data Index: 57460 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.2349. Min Act: -0.1700
Data Index: 3878655 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.1724. Min Act: -0.1700
Data Index: 4816722 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.1411. Min Act: -0.1700
Data Index: 7127104 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.1411. Min Act: -0.1700
Data Index: 3706914 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.1411. Min Act: -0.1700
Data Index: 2717904 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.1099. Min Act: -0.1700
Data Index: 8431625 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.1099. Min Act: -0.1700
Data Index: 4859680 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.1099. Min Act: -0.1700
Data Index: 2628940 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.0786. Min Act: -0.1700
Data Index: 1706937 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.0786. Min Act: -0.1700
Data Index: 429368 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.0474. Min Act: -0.1700
Data Index: 3587582 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.0474. Min Act: -0.1700
Data Index: 4704696 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.0161. Min Act: -0.1700
Data Index: 8663812 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.0161. Min Act: -0.1700
Data Index: 8534505 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5786. Min Range: -6.5786
Max Act: 6.0161. Min Act: -0.1700
Data Index: 8740226 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5786. Min Range: -6.5786
Max Act: 5.9849. Min Act: -0.1700
Data Index: 2747383 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5786. Min Range: -6.5786
Max Act: 5.9536. Min Act: -0.1700
Data Index: 1465672 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5786. Min Range: -6.5786
Max Act: 5.9224. Min Act: -0.1700
Data Index: 1324954 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5786. Min Range: -6.5786
Max Act: 5.9536. Min Act: -0.1700
Data Index: 4084623 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19