Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.6015. Min Act: -0.1700
Data Index: 4045433 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.5078. Min Act: -0.1700
Data Index: 3654662 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.4453. Min Act: -0.1700
Data Index: 3750754 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3828. Min Act: -0.1700
Data Index: 7566290 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3828. Min Act: -0.1700
Data Index: 4918616 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3828. Min Act: -0.1700
Data Index: 4664601 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3515. Min Act: -0.1700
Data Index: 6870285 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3515. Min Act: -0.1700
Data Index: 2048116 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3203. Min Act: -0.1700
Data Index: 1437811 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3203. Min Act: -0.1700
Data Index: 4710751 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2890. Min Act: -0.1700
Data Index: 8731055 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.1700
Data Index: 6075482 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.1700
Data Index: 4337946 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.1700
Data Index: 4333415 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1328. Min Act: -0.1700
Data Index: 5299045 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1328. Min Act: -0.1700
Data Index: 1560991 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1328. Min Act: -0.1700
Data Index: 6732337 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1328. Min Act: -0.1700
Data Index: 5125078 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 422447 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1328. Min Act: -0.1700
Data Index: 6792333 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19