Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 975 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9311. Min Range: -6.9311
Max Act: 6.9311. Min Act: -0.1700
Data Index: 22649 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9311. Min Range: -6.9311
Max Act: 6.2749. Min Act: -0.1700
Data Index: 6899753 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9311. Min Range: -6.9311
Max Act: 6.1186. Min Act: -0.1700
Data Index: 1470898 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.9624. Min Act: -0.1700
Data Index: 2989312 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.9624. Min Act: -0.1700
Data Index: 2187634 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.9936. Min Act: -0.1700
Data Index: 3211598 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.8686. Min Act: -0.1700
Data Index: 7845633 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.8686. Min Act: -0.1700
Data Index: 1553115 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.8061. Min Act: -0.1700
Data Index: 8453178 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.8061. Min Act: -0.1700
Data Index: 4763653 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.8061. Min Act: -0.1700
Data Index: 3671649 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.8061. Min Act: -0.1700
Data Index: 1068940 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.7749. Min Act: -0.1700
Data Index: 4999427 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.7749. Min Act: -0.1700
Data Index: 3342275 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.7749. Min Act: -0.1700
Data Index: 3495000 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.7749. Min Act: -0.1700
Data Index: 1814507 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.7749. Min Act: -0.1700
Data Index: 6089655 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.7436. Min Act: -0.1700
Data Index: 2390064 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.7436. Min Act: -0.1700
Data Index: 5108482 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9311. Min Range: -6.9311
Max Act: 5.7436. Min Act: -0.1700
Data Index: 3717790 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19