Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 175 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.5697. Min Act: -0.1700
Data Index: 8675009 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.3197. Min Act: -0.1700
Data Index: 6002631 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.2572. Min Act: -0.1700
Data Index: 8682888 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.2572. Min Act: -0.1700
Data Index: 2400319 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.1322. Min Act: -0.1700
Data Index: 7379752 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.1010. Min Act: -0.1700
Data Index: 1624786 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.0385. Min Act: -0.1700
Data Index: 8799588 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.0385. Min Act: -0.1700
Data Index: 4383450 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.0385. Min Act: -0.1700
Data Index: 8697928 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.0385. Min Act: -0.1700
Data Index: 4411787 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.0385. Min Act: -0.1700
Data Index: 481118 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.0072. Min Act: -0.1700
Data Index: 2448576 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5697. Min Range: -6.5697
Max Act: 6.0072. Min Act: -0.1700
Data Index: 8027623 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5697. Min Range: -6.5697
Max Act: 5.9760. Min Act: -0.1700
Data Index: 6764208 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5697. Min Range: -6.5697
Max Act: 5.9760. Min Act: -0.1700
Data Index: 407996 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5697. Min Range: -6.5697
Max Act: 5.9760. Min Act: -0.1700
Data Index: 2376680 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5697. Min Range: -6.5697
Max Act: 5.9760. Min Act: -0.1700
Data Index: 7073516 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5697. Min Range: -6.5697
Max Act: 5.9447. Min Act: -0.1700
Data Index: 619966 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5697. Min Range: -6.5697
Max Act: 5.9447. Min Act: -0.1700
Data Index: 2448577 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5697. Min Range: -6.5697
Max Act: 5.9135. Min Act: -0.1700
Data Index: 6850464 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19