Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4185 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.5769. Min Act: -0.1700
Data Index: 5157572 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.2957. Min Act: -0.1700
Data Index: 2889093 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.2332. Min Act: -0.1700
Data Index: 2330291 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.2644. Min Act: -0.1700
Data Index: 2601477 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.2644. Min Act: -0.1700
Data Index: 7579794 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.2644. Min Act: -0.1700
Data Index: 7593978 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.1394. Min Act: -0.1700
Data Index: 788551 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.1394. Min Act: -0.1700
Data Index: 5959357 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.1707. Min Act: -0.1700
Data Index: 2032137 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.1081. Min Act: -0.1700
Data Index: 1236109 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.1081. Min Act: -0.1700
Data Index: 7971774 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.1081. Min Act: -0.1700
Data Index: 6405374 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.0769. Min Act: -0.1700
Data Index: 7071130 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.0769. Min Act: -0.1700
Data Index: 2441244 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.0769. Min Act: -0.1700
Data Index: 6128241 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.0769. Min Act: -0.1700
Data Index: 1531864 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.0769. Min Act: -0.1700
Data Index: 1631458 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.0769. Min Act: -0.1700
Data Index: 6384954 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.0456. Min Act: -0.1700
Data Index: 3997292 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5769. Min Range: -4.5769
Max Act: 4.0456. Min Act: -0.1700
Data Index: 5648627 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19