Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1692
Data Index: 4583969 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1698
Data Index: 8648763 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1700
Data Index: 4712757 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1638
Data Index: 8552967 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1685
Data Index: 5709839 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1700
Data Index: 4052399 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1699
Data Index: 7849507 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1686
Data Index: 963820 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1693
Data Index: 1637935 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1700
Data Index: 4776666 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1337. Min Range: -2.1337
Max Act: 2.1337. Min Act: -0.1699
Data Index: 3318801 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.9993. Min Act: -0.1700
Data Index: 3292685 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.9824. Min Act: -0.1696
Data Index: 1626517 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.8804. Min Act: -0.1699
Data Index: 2674423 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.8804. Min Act: -0.1699
Data Index: 701671 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.8804. Min Act: -0.1685
Data Index: 4826238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.8804. Min Act: -0.1700
Data Index: 5169013 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.8804. Min Act: -0.1700
Data Index: 7710814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.8804. Min Act: -0.1699
Data Index: 889063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1337. Min Range: -2.1337
Max Act: 1.8804. Min Act: -0.1699
Data Index: 6069507 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19