Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.4955. Min Act: -0.1700
Data Index: 7787192 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.2142. Min Act: -0.1700
Data Index: 6993934 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.2142. Min Act: -0.1700
Data Index: 1491656 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.1517. Min Act: -0.1700
Data Index: 7590925 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.0892. Min Act: -0.1700
Data Index: 7485451 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.0267. Min Act: -0.1700
Data Index: 2848024 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.0580. Min Act: -0.1700
Data Index: 5367233 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.0267. Min Act: -0.1700
Data Index: 6939932 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.0267. Min Act: -0.1700
Data Index: 5070714 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4955. Min Range: -7.4955
Max Act: 7.0267. Min Act: -0.1700
Data Index: 7252848 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.9955. Min Act: -0.1700
Data Index: 1923824 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.9330. Min Act: -0.1700
Data Index: 2298940 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.9330. Min Act: -0.1700
Data Index: 8502757 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.9017. Min Act: -0.1700
Data Index: 7620574 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.9017. Min Act: -0.1700
Data Index: 5208262 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.9330. Min Act: -0.1700
Data Index: 2911336 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.9017. Min Act: -0.1700
Data Index: 3205437 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.8705. Min Act: -0.1700
Data Index: 1775407 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.8705. Min Act: -0.1700
Data Index: 4971523 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4955. Min Range: -7.4955
Max Act: 6.8705. Min Act: -0.1700
Data Index: 5707067 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19