Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2233 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.7782. Min Act: -0.1691
Data Index: 4200101 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.7782. Min Act: -0.1697
Data Index: 6790435 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.7782. Min Act: -0.1700
Data Index: 3954435 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.7782. Min Act: -0.1695
Data Index: 1103635 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.7782. Min Act: -0.1680
Data Index: 6489137 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.7782. Min Act: -0.1700
Data Index: 3205297 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.7782. Min Act: -0.1696
Data Index: 1290022 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.7121. Min Act: -0.1693
Data Index: 6652814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6795. Min Act: -0.1693
Data Index: 3309658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6795. Min Act: -0.1700
Data Index: 5733106 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6633. Min Act: -0.1650
Data Index: 1878410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6633. Min Act: -0.1624
Data Index: 4765763 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6633. Min Act: -0.1672
Data Index: 5585676 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6472. Min Act: -0.1700
Data Index: 6854567 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6472. Min Act: -0.1697
Data Index: 7071092 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6313. Min Act: -0.1687
Data Index: 2728377 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6313. Min Act: -0.1699
Data Index: 2011437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6313. Min Act: -0.1671
Data Index: 8213529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6313. Min Act: -0.1700
Data Index: 4000403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7782. Min Range: -0.7782
Max Act: 0.6313. Min Act: -0.1700
Data Index: 2680177 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19