Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6332 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0557. Min Range: -9.0557
Max Act: 9.0557. Min Act: -0.1700
Data Index: 7896941 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.6182. Min Act: -0.1700
Data Index: 5255894 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.6182. Min Act: -0.1700
Data Index: 314956 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.6182. Min Act: -0.1700
Data Index: 1440995 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.5557. Min Act: -0.1700
Data Index: 1928610 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.5557. Min Act: -0.1700
Data Index: 6220871 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.4307. Min Act: -0.1700
Data Index: 807830 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.4307. Min Act: -0.1700
Data Index: 1653940 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.3682. Min Act: -0.1700
Data Index: 5980463 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.3682. Min Act: -0.1700
Data Index: 5532951 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.3682. Min Act: -0.1700
Data Index: 3899392 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.3682. Min Act: -0.1700
Data Index: 7088087 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.3057. Min Act: -0.1700
Data Index: 6890977 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.2432. Min Act: -0.1700
Data Index: 4248855 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.2432. Min Act: -0.1700
Data Index: 8415547 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 6224165 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 6583895 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 4693309 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.1182. Min Act: -0.1700
Data Index: 7564865 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0557. Min Range: -9.0557
Max Act: 8.0557. Min Act: -0.1700
Data Index: 6000259 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19