Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5053 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1620. Min Range: -7.1620
Max Act: 7.1620. Min Act: -0.1700
Data Index: 3481838 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1620. Min Range: -7.1620
Max Act: 7.0995. Min Act: -0.1700
Data Index: 7131784 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1620. Min Range: -7.1620
Max Act: 7.0370. Min Act: -0.1700
Data Index: 2481489 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.9745. Min Act: -0.1700
Data Index: 6400423 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.9432. Min Act: -0.1700
Data Index: 4846904 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.9120. Min Act: -0.1700
Data Index: 4795362 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.9120. Min Act: -0.1700
Data Index: 6908918 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.8495. Min Act: -0.1700
Data Index: 8032336 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.8182. Min Act: -0.1700
Data Index: 2012230 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.8182. Min Act: -0.1700
Data Index: 2104017 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7870. Min Act: -0.1700
Data Index: 94390 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7870. Min Act: -0.1700
Data Index: 77137 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7557. Min Act: -0.1700
Data Index: 85318 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7557. Min Act: -0.1700
Data Index: 1854260 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7557. Min Act: -0.1700
Data Index: 4654159 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7245. Min Act: -0.1700
Data Index: 7363038 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7245. Min Act: -0.1700
Data Index: 5753344 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7557. Min Act: -0.1700
Data Index: 2406752 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.7245. Min Act: -0.1700
Data Index: 1146845 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1620. Min Range: -7.1620
Max Act: 6.6932. Min Act: -0.1700
Data Index: 6208596 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19