Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.8643. Min Act: -0.1700
Data Index: 7614397 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.8017. Min Act: -0.1700
Data Index: 6490659 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.8017. Min Act: -0.1700
Data Index: 365437 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.8017. Min Act: -0.1700
Data Index: 7624872 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.8017. Min Act: -0.1700
Data Index: 7901071 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 7517485 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7392. Min Act: -0.1700
Data Index: 6127823 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 5821602 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 5695762 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 1620504 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 622568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 4829763 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 1429166 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 7629387 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 7554453 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7705. Min Act: -0.1700
Data Index: 3773032 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7392. Min Act: -0.1700
Data Index: 1208415 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7392. Min Act: -0.1700
Data Index: 4985329 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7392. Min Act: -0.1700
Data Index: 945622 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8643. Min Range: -3.8643
Max Act: 3.7392. Min Act: -0.1700
Data Index: 5129331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19