Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3926 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5872. Min Act: -0.1700
Data Index: 7458612 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.6185. Min Act: -0.1700
Data Index: 3669068 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5872. Min Act: -0.1700
Data Index: 7145060 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5872. Min Act: -0.1700
Data Index: 2136383 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5872. Min Act: -0.1700
Data Index: 6434746 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5559. Min Act: -0.1700
Data Index: 5475386 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5559. Min Act: -0.1700
Data Index: 7536823 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5559. Min Act: -0.1700
Data Index: 1491746 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5559. Min Act: -0.1700
Data Index: 3375301 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 5331222 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 2470460 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 5345889 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 5436019 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 5443947 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 4159104 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 6693403 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5559. Min Act: -0.1700
Data Index: 6920560 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 1262457 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 6989112 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6185. Min Range: -3.6185
Max Act: 3.5246. Min Act: -0.1700
Data Index: 2478332 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19