Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.8534. Min Act: -0.1700
Data Index: 838869 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.7909. Min Act: -0.1700
Data Index: 4047418 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.8221. Min Act: -0.1700
Data Index: 1018660 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.6659. Min Act: -0.1700
Data Index: 8546167 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.6659. Min Act: -0.1700
Data Index: 7565003 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.6659. Min Act: -0.1700
Data Index: 8187971 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.5721. Min Act: -0.1700
Data Index: 8663698 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.6034. Min Act: -0.1700
Data Index: 1288865 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.5721. Min Act: -0.1700
Data Index: 1062724 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.5409. Min Act: -0.1700
Data Index: 2873799 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.5409. Min Act: -0.1700
Data Index: 5974296 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.5409. Min Act: -0.1700
Data Index: 4860253 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.5096. Min Act: -0.1700
Data Index: 5123415 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.4784. Min Act: -0.1700
Data Index: 1518019 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.4159. Min Act: -0.1700
Data Index: 5451644 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.4159. Min Act: -0.1700
Data Index: 241923 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.4159. Min Act: -0.1700
Data Index: 6880523 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.3846. Min Act: -0.1700
Data Index: 7117224 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.4159. Min Act: -0.1700
Data Index: 2851458 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8534. Min Range: -6.8534
Max Act: 6.3846. Min Act: -0.1700
Data Index: 1066462 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19