Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.6213. Min Act: -0.1700
Data Index: 2865067 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.5900. Min Act: -0.1700
Data Index: 782133 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.5275. Min Act: -0.1700
Data Index: 2964236 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.4025. Min Act: -0.1700
Data Index: 4504845 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.4025. Min Act: -0.1700
Data Index: 4131103 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.3400. Min Act: -0.1700
Data Index: 6056541 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.3088. Min Act: -0.1700
Data Index: 5436376 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.3088. Min Act: -0.1700
Data Index: 4887385 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.2463. Min Act: -0.1700
Data Index: 3464914 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.2150. Min Act: -0.1700
Data Index: 8360131 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.2150. Min Act: -0.1700
Data Index: 4192461 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1838. Min Act: -0.1700
Data Index: 6110221 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1838. Min Act: -0.1700
Data Index: 8360132 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1525. Min Act: -0.1700
Data Index: 4734794 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1525. Min Act: -0.1700
Data Index: 6035525 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1838. Min Act: -0.1700
Data Index: 6473462 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1838. Min Act: -0.1700
Data Index: 3671748 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1213. Min Act: -0.1700
Data Index: 1591234 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1213. Min Act: -0.1700
Data Index: 40238 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6213. Min Range: -7.6213
Max Act: 7.1213. Min Act: -0.1700
Data Index: 6865311 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19