Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.1559. Min Act: -0.1700
Data Index: 4437598 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.1087. Min Act: -0.1700
Data Index: 3782896 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0771. Min Act: -0.1700
Data Index: 3296052 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0298. Min Act: -0.1700
Data Index: 2303725 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9824. Min Act: -0.1700
Data Index: 7849982 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9982. Min Act: -0.1700
Data Index: 5265887 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9982. Min Act: -0.1700
Data Index: 3955361 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9824. Min Act: -0.1700
Data Index: 3444606 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9824. Min Act: -0.1700
Data Index: 208996 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9666. Min Act: -0.1700
Data Index: 3740167 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9666. Min Act: -0.1700
Data Index: 4766046 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9666. Min Act: -0.1700
Data Index: 67405 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9508. Min Act: -0.1700
Data Index: 2886551 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9666. Min Act: -0.1700
Data Index: 4479944 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9824. Min Act: -0.1700
Data Index: 8764315 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9508. Min Act: -0.1700
Data Index: 3782894 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9508. Min Act: -0.1700
Data Index: 6429559 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9508. Min Act: -0.1700
Data Index: 3635477 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9508. Min Act: -0.1700
Data Index: 7443426 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9508. Min Act: -0.1700
Data Index: 4904965 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19