Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.9718. Min Act: -0.1700
Data Index: 4717574 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.8780. Min Act: -0.1700
Data Index: 5058448 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.8468. Min Act: -0.1700
Data Index: 2117265 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.8468. Min Act: -0.1700
Data Index: 3361967 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7843. Min Act: -0.1700
Data Index: 4492929 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.8155. Min Act: -0.1700
Data Index: 7904065 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7843. Min Act: -0.1700
Data Index: 5325595 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7843. Min Act: -0.1700
Data Index: 1279966 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 157216 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 2246100 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 1345036 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 1633988 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 8830716 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7843. Min Act: -0.1700
Data Index: 5305985 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 7581141 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 7363015 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7218. Min Act: -0.1700
Data Index: 1138602 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 5750135 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7530. Min Act: -0.1700
Data Index: 6383843 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9718. Min Range: -4.9718
Max Act: 4.7218. Min Act: -0.1700
Data Index: 591282 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19