Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1203 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3188. Min Range: -4.3188
Max Act: 4.3188. Min Act: -0.1700
Data Index: 2869742 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3188. Min Range: -4.3188
Max Act: 4.1626. Min Act: -0.1700
Data Index: 523059 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.9750. Min Act: -0.1700
Data Index: 6560341 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.9281. Min Act: -0.1700
Data Index: 5712600 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.9281. Min Act: -0.1700
Data Index: 7908353 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.9125. Min Act: -0.1700
Data Index: 5690037 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8969. Min Act: -0.1700
Data Index: 850780 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8812. Min Act: -0.1700
Data Index: 1044424 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8812. Min Act: -0.1700
Data Index: 7194385 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8500. Min Act: -0.1700
Data Index: 4346705 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8656. Min Act: -0.1700
Data Index: 7626454 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8656. Min Act: -0.1700
Data Index: 5869251 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8656. Min Act: -0.1700
Data Index: 1001055 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8187. Min Act: -0.1700
Data Index: 3208889 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.7874. Min Act: -0.1700
Data Index: 6392184 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.8030. Min Act: -0.1700
Data Index: 7931229 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.7718. Min Act: -0.1700
Data Index: 7748905 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.7874. Min Act: -0.1700
Data Index: 3857969 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.7874. Min Act: -0.1700
Data Index: 3259961 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3188. Min Range: -4.3188
Max Act: 3.7405. Min Act: -0.1700
Data Index: 5006919 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19