Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2047 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.7014. Min Act: -0.1700
Data Index: 5094869 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.5764. Min Act: -0.1700
Data Index: 6967891 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.5139. Min Act: -0.1700
Data Index: 2323019 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.5139. Min Act: -0.1700
Data Index: 7960946 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.5139. Min Act: -0.1700
Data Index: 5134904 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.4514. Min Act: -0.1700
Data Index: 3594001 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.4514. Min Act: -0.1700
Data Index: 1926116 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.4514. Min Act: -0.1700
Data Index: 8433475 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.4514. Min Act: -0.1700
Data Index: 3975291 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.4514. Min Act: -0.1700
Data Index: 4010735 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.3889. Min Act: -0.1700
Data Index: 5993595 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.3889. Min Act: -0.1700
Data Index: 3152841 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.3264. Min Act: -0.1700
Data Index: 8296969 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.3264. Min Act: -0.1700
Data Index: 144774 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.2639. Min Act: -0.1700
Data Index: 3913646 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.2639. Min Act: -0.1700
Data Index: 619608 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.2639. Min Act: -0.1700
Data Index: 7628097 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.2014. Min Act: -0.1700
Data Index: 2729126 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.2014. Min Act: -0.1700
Data Index: 1003363 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7014. Min Range: -8.7014
Max Act: 8.2014. Min Act: -0.1700
Data Index: 669746 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19