Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.9340. Min Act: -0.1700
Data Index: 7715335 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.4653. Min Act: -0.1700
Data Index: 3699910 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.4028. Min Act: -0.1700
Data Index: 3288490 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.3715. Min Act: -0.1700
Data Index: 4269891 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.3403. Min Act: -0.1700
Data Index: 2751976 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.3090. Min Act: -0.1700
Data Index: 2991933 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.3090. Min Act: -0.1700
Data Index: 510628 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.2778. Min Act: -0.1700
Data Index: 1439033 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.2778. Min Act: -0.1700
Data Index: 1438411 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.2465. Min Act: -0.1700
Data Index: 1125521 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.2153. Min Act: -0.1700
Data Index: 7449794 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.2153. Min Act: -0.1700
Data Index: 7111654 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.1840. Min Act: -0.1700
Data Index: 6218344 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.1528. Min Act: -0.1700
Data Index: 561741 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.1840. Min Act: -0.1700
Data Index: 2072430 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.1840. Min Act: -0.1700
Data Index: 500814 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.1840. Min Act: -0.1700
Data Index: 357353 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3013739 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3750495 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9340. Min Range: -5.9340
Max Act: 5.1215. Min Act: -0.1700
Data Index: 1434848 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19