Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.9591. Min Act: -0.1700
Data Index: 2318490 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.6466. Min Act: -0.1700
Data Index: 8700896 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.6466. Min Act: -0.1700
Data Index: 6000289 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.5841. Min Act: -0.1700
Data Index: 6498343 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.5841. Min Act: -0.1700
Data Index: 630670 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.5216. Min Act: -0.1700
Data Index: 6791658 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.5216. Min Act: -0.1700
Data Index: 6409270 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.5216. Min Act: -0.1700
Data Index: 4492830 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.5216. Min Act: -0.1700
Data Index: 4261458 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.4591. Min Act: -0.1700
Data Index: 890333 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.4591. Min Act: -0.1700
Data Index: 2396844 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.4591. Min Act: -0.1700
Data Index: 5842742 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.4591. Min Act: -0.1700
Data Index: 8714282 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.4591. Min Act: -0.1700
Data Index: 8686615 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.4591. Min Act: -0.1700
Data Index: 1637631 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.4591. Min Act: -0.1700
Data Index: 6794724 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.3966. Min Act: -0.1700
Data Index: 1734421 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.3966. Min Act: -0.1700
Data Index: 5839182 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.3966. Min Act: -0.1700
Data Index: 8648423 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9591. Min Range: -8.9591
Max Act: 8.3966. Min Act: -0.1700
Data Index: 3194199 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19