Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.3606. Min Act: -0.1700
Data Index: 2500396 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.2981. Min Act: -0.1700
Data Index: 5276550 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.2669. Min Act: -0.1700
Data Index: 3277535 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.2044. Min Act: -0.1700
Data Index: 7142828 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.2669. Min Act: -0.1700
Data Index: 4399825 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.2356. Min Act: -0.1700
Data Index: 1252972 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.2044. Min Act: -0.1700
Data Index: 1835901 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.2044. Min Act: -0.1700
Data Index: 3842743 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.1731. Min Act: -0.1700
Data Index: 3482063 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.1731. Min Act: -0.1700
Data Index: 2873833 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.1731. Min Act: -0.1700
Data Index: 2871884 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.1731. Min Act: -0.1700
Data Index: 5584455 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.1419. Min Act: -0.1700
Data Index: 719763 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.1419. Min Act: -0.1700
Data Index: 6266883 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.1419. Min Act: -0.1700
Data Index: 1639607 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.0481. Min Act: -0.1700
Data Index: 5264938 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.0481. Min Act: -0.1700
Data Index: 2955744 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.0481. Min Act: -0.1700
Data Index: 5211742 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3606. Min Range: -5.3606
Max Act: 5.0169. Min Act: -0.1700
Data Index: 4352154 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3606. Min Range: -5.3606
Max Act: 4.9856. Min Act: -0.1700
Data Index: 467892 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19