Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.8736. Min Act: -0.1700
Data Index: 221400 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.7799. Min Act: -0.1700
Data Index: 2621738 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.7799. Min Act: -0.1700
Data Index: 6098805 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.7486. Min Act: -0.1700
Data Index: 4105985 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.6549. Min Act: -0.1700
Data Index: 3604524 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.6236. Min Act: -0.1700
Data Index: 5149792 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.5611. Min Act: -0.1700
Data Index: 7864669 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.5611. Min Act: -0.1700
Data Index: 2018050 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.5611. Min Act: -0.1700
Data Index: 5804253 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.5299. Min Act: -0.1700
Data Index: 3536685 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.5299. Min Act: -0.1700
Data Index: 2187182 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.5299. Min Act: -0.1700
Data Index: 900576 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4986. Min Act: -0.1700
Data Index: 7365003 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4674. Min Act: -0.1700
Data Index: 7966528 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4674. Min Act: -0.1700
Data Index: 6431366 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4674. Min Act: -0.1700
Data Index: 5529070 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4361. Min Act: -0.1700
Data Index: 4960224 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4361. Min Act: -0.1700
Data Index: 7543977 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4361. Min Act: -0.1700
Data Index: 6848334 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8736. Min Range: -6.8736
Max Act: 6.4361. Min Act: -0.1700
Data Index: 389345 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19