Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.3472. Min Act: -0.1700
Data Index: 3083299 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2535. Min Act: -0.1700
Data Index: 2398915 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2222. Min Act: -0.1697
Data Index: 508603 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2222. Min Act: -0.1700
Data Index: 821522 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1910. Min Act: -0.1700
Data Index: 2315054 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1597. Min Act: -0.1700
Data Index: 3083297 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1597. Min Act: -0.1700
Data Index: 6515643 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1285. Min Act: -0.1700
Data Index: 7442973 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1285. Min Act: -0.1700
Data Index: 6753918 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0972. Min Act: -0.1700
Data Index: 8199685 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0972. Min Act: -0.1700
Data Index: 5960276 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0972. Min Act: -0.1700
Data Index: 5418889 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0972. Min Act: -0.1700
Data Index: 2808423 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0660. Min Act: -0.1700
Data Index: 3989891 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0972. Min Act: -0.1700
Data Index: 7624013 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0972. Min Act: -0.1700
Data Index: 3083294 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0660. Min Act: -0.1700
Data Index: 166447 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0660. Min Act: -0.1700
Data Index: 1421474 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0660. Min Act: -0.1700
Data Index: 6872661 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.0660. Min Act: -0.1700
Data Index: 1525927 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19