Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1787. Min Range: -6.1787
Max Act: 6.1787. Min Act: -0.1700
Data Index: 1383080 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.9287. Min Act: -0.1700
Data Index: 581205 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8974. Min Act: -0.1700
Data Index: 1318669 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8974. Min Act: -0.1700
Data Index: 1318670 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8974. Min Act: -0.1700
Data Index: 1723131 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8974. Min Act: -0.1700
Data Index: 3109774 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8974. Min Act: -0.1700
Data Index: 6429624 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8662. Min Act: -0.1700
Data Index: 2480745 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8662. Min Act: -0.1700
Data Index: 3543637 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8662. Min Act: -0.1700
Data Index: 3525756 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8662. Min Act: -0.1700
Data Index: 3052034 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8662. Min Act: -0.1700
Data Index: 2148062 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8662. Min Act: -0.1700
Data Index: 6126209 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8349. Min Act: -0.1700
Data Index: 2186327 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8349. Min Act: -0.1700
Data Index: 3212849 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.8037. Min Act: -0.1700
Data Index: 8618807 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.7724. Min Act: -0.1700
Data Index: 1031444 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.7724. Min Act: -0.1700
Data Index: 8133959 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.7724. Min Act: -0.1700
Data Index: 7119779 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1787. Min Range: -6.1787
Max Act: 5.7412. Min Act: -0.1700
Data Index: 2624051 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19