Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0334. Min Range: -6.0334
Max Act: 6.0334. Min Act: -0.1700
Data Index: 7117919 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0334. Min Range: -6.0334
Max Act: 6.0022. Min Act: -0.1700
Data Index: 6473959 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.9397. Min Act: -0.1700
Data Index: 1995385 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.9397. Min Act: -0.1700
Data Index: 6473960 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.9397. Min Act: -0.1696
Data Index: 2758564 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.9084. Min Act: -0.1700
Data Index: 2519157 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.9084. Min Act: -0.1700
Data Index: 5103444 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.8772. Min Act: -0.1700
Data Index: 842978 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.8772. Min Act: -0.1700
Data Index: 5301277 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5610941 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.8147. Min Act: -0.1700
Data Index: 6718445 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 184579 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 2960549 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 733184 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5122800 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 3671006 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5796178 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5745789 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7522. Min Act: -0.1700
Data Index: 5103449 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7522. Min Act: -0.1700
Data Index: 2788739 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19