Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3887. Min Range: -9.3887
Max Act: 9.3887. Min Act: -0.1700
Data Index: 5028603 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3887. Min Range: -9.3887
Max Act: 9.0762. Min Act: -0.1700
Data Index: 26073 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3887. Min Range: -9.3887
Max Act: 9.0762. Min Act: -0.1700
Data Index: 1733499 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.8262. Min Act: -0.1700
Data Index: 7369831 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.7012. Min Act: -0.1700
Data Index: 5882647 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.7012. Min Act: -0.1700
Data Index: 6812547 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.6387. Min Act: -0.1700
Data Index: 4593098 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.5762. Min Act: -0.1700
Data Index: 8642134 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.5762. Min Act: -0.1700
Data Index: 8203886 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.5762. Min Act: -0.1700
Data Index: 8587215 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.5762. Min Act: -0.1700
Data Index: 6578896 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.5137. Min Act: -0.1700
Data Index: 7693285 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.3887. Min Act: -0.1700
Data Index: 8548265 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.4512. Min Act: -0.1700
Data Index: 1095998 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.4512. Min Act: -0.1700
Data Index: 4189185 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.4512. Min Act: -0.1700
Data Index: 3117715 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.4512. Min Act: -0.1700
Data Index: 2562701 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.4512. Min Act: -0.1700
Data Index: 1553551 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.3887. Min Act: -0.1700
Data Index: 2224143 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3887. Min Range: -9.3887
Max Act: 8.3887. Min Act: -0.1700
Data Index: 7874525 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19