Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2540 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6914. Min Act: -0.1700
Data Index: 6304072 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6754. Min Act: -0.1700
Data Index: 1400544 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6593. Min Act: -0.1700
Data Index: 5391871 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6433. Min Act: -0.1700
Data Index: 2237677 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6433. Min Act: -0.1700
Data Index: 6302892 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6593. Min Act: -0.1700
Data Index: 6279907 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6433. Min Act: -0.1700
Data Index: 5041141 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6111. Min Act: -0.1700
Data Index: 4502239 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6111. Min Act: -0.1700
Data Index: 5219566 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5950. Min Act: -0.1700
Data Index: 1350821 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5950. Min Act: -0.1700
Data Index: 1708044 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.6111. Min Act: -0.1700
Data Index: 6269290 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5789. Min Act: -0.1700
Data Index: 6178167 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5789. Min Act: -0.1700
Data Index: 6088088 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5789. Min Act: -0.1700
Data Index: 607328 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5789. Min Act: -0.1700
Data Index: 1898268 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5789. Min Act: -0.1700
Data Index: 6359225 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5628. Min Act: -0.1700
Data Index: 145782 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5789. Min Act: -0.1700
Data Index: 4359020 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6914. Min Range: -2.6914
Max Act: 2.5950. Min Act: -0.1700
Data Index: 4356504 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19