Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1346. Min Range: -6.1346
Max Act: 6.1346. Min Act: -0.1700
Data Index: 2187446 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1346. Min Range: -6.1346
Max Act: 6.0721. Min Act: -0.1700
Data Index: 4893854 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1346. Min Range: -6.1346
Max Act: 6.0096. Min Act: -0.1700
Data Index: 668114 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.9784. Min Act: -0.1700
Data Index: 426393 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.9784. Min Act: -0.1700
Data Index: 3079720 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.9784. Min Act: -0.1700
Data Index: 3982995 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.9471. Min Act: -0.1700
Data Index: 6383874 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.9471. Min Act: -0.1700
Data Index: 3983009 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.9159. Min Act: -0.1700
Data Index: 2212849 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.9159. Min Act: -0.1700
Data Index: 596408 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.8846. Min Act: -0.1700
Data Index: 6743836 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.8221. Min Act: -0.1700
Data Index: 4365896 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.8221. Min Act: -0.1700
Data Index: 2292191 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.8221. Min Act: -0.1700
Data Index: 6394829 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.8221. Min Act: -0.1700
Data Index: 231281 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.7909. Min Act: -0.1700
Data Index: 1507987 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.7909. Min Act: -0.1700
Data Index: 1508009 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.7596. Min Act: -0.1700
Data Index: 3475785 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.7284. Min Act: -0.1700
Data Index: 2074287 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1346. Min Range: -6.1346
Max Act: 5.7284. Min Act: -0.1700
Data Index: 4975322 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19