Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 65 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1361. Min Range: -7.1361
Max Act: 7.1361. Min Act: -0.1700
Data Index: 3185381 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1361. Min Range: -7.1361
Max Act: 7.0111. Min Act: -0.1700
Data Index: 6229446 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.9174. Min Act: -0.1700
Data Index: 2590298 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.9174. Min Act: -0.1700
Data Index: 7163978 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.8861. Min Act: -0.1700
Data Index: 7300077 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.8861. Min Act: -0.1700
Data Index: 479491 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.8861. Min Act: -0.1700
Data Index: 4448101 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.8549. Min Act: -0.1700
Data Index: 6626507 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.8549. Min Act: -0.1700
Data Index: 7415294 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.8549. Min Act: -0.1700
Data Index: 2422146 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.8549. Min Act: -0.1700
Data Index: 8292345 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.7924. Min Act: -0.1700
Data Index: 3611880 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.7924. Min Act: -0.1700
Data Index: 5082070 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.7611. Min Act: -0.1700
Data Index: 8354344 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.7611. Min Act: -0.1700
Data Index: 8558191 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.7611. Min Act: -0.1700
Data Index: 341378 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.7611. Min Act: -0.1700
Data Index: 376174 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.7611. Min Act: -0.1700
Data Index: 7481808 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.6986. Min Act: -0.1700
Data Index: 3771181 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1361. Min Range: -7.1361
Max Act: 6.7299. Min Act: -0.1700
Data Index: 6770691 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19