Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0718. Min Range: -5.0718
Max Act: 5.0718. Min Act: -0.1700
Data Index: 6238903 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0718. Min Range: -5.0718
Max Act: 5.0405. Min Act: -0.1700
Data Index: 6432065 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.9468. Min Act: -0.1700
Data Index: 2753613 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.9155. Min Act: -0.1700
Data Index: 2578242 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.8843. Min Act: -0.1700
Data Index: 3253332 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.8530. Min Act: -0.1700
Data Index: 6051720 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.8218. Min Act: -0.1700
Data Index: 5591806 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7280. Min Act: -0.1700
Data Index: 4228097 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6968. Min Act: -0.1700
Data Index: 2691392 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6655. Min Act: -0.1700
Data Index: 5553462 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6343. Min Act: -0.1700
Data Index: 4175905 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6030. Min Act: -0.1700
Data Index: 3282990 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6343. Min Act: -0.1700
Data Index: 7041970 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6343. Min Act: -0.1700
Data Index: 3993795 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6030. Min Act: -0.1700
Data Index: 6807239 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6030. Min Act: -0.1700
Data Index: 449155 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.5405. Min Act: -0.1700
Data Index: 4851777 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.5718. Min Act: -0.1700
Data Index: 882153 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.5718. Min Act: -0.1700
Data Index: 1473275 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.5405. Min Act: -0.1700
Data Index: 6368677 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19