Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1767 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1141. Min Range: -6.1141
Max Act: 6.0829. Min Act: -0.1700
Data Index: 8345575 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1141. Min Range: -6.1141
Max Act: 6.1141. Min Act: -0.1700
Data Index: 1114430 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.9891. Min Act: -0.1700
Data Index: 2220908 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.9891. Min Act: -0.1700
Data Index: 3861354 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.8016. Min Act: -0.1700
Data Index: 1780737 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.7391. Min Act: -0.1700
Data Index: 4582947 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.7079. Min Act: -0.1700
Data Index: 3604393 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.6766. Min Act: -0.1700
Data Index: 5438300 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.6454. Min Act: -0.1700
Data Index: 153153 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.6454. Min Act: -0.1700
Data Index: 7938820 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.6454. Min Act: -0.1700
Data Index: 5145362 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.6141. Min Act: -0.1700
Data Index: 6959824 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.6141. Min Act: -0.1700
Data Index: 2283401 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.5829. Min Act: -0.1700
Data Index: 7860231 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.5829. Min Act: -0.1700
Data Index: 7673966 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.5829. Min Act: -0.1700
Data Index: 4272812 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.5204. Min Act: -0.1700
Data Index: 7112006 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.5204. Min Act: -0.1700
Data Index: 2721141 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.5204. Min Act: -0.1700
Data Index: 7158564 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1141. Min Range: -6.1141
Max Act: 5.5516. Min Act: -0.1700
Data Index: 8572710 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19