Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1727. Min Range: -5.1727
Max Act: 5.1727. Min Act: -0.1700
Data Index: 752794 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1727. Min Range: -5.1727
Max Act: 5.1727. Min Act: -0.1700
Data Index: 3152577 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1727. Min Range: -5.1727
Max Act: 5.0789. Min Act: -0.1700
Data Index: 28927 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1727. Min Range: -5.1727
Max Act: 5.0164. Min Act: -0.1700
Data Index: 7375635 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1727. Min Range: -5.1727
Max Act: 5.0164. Min Act: -0.1700
Data Index: 8215111 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1727. Min Range: -5.1727
Max Act: 5.0164. Min Act: -0.1700
Data Index: 2680309 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9852. Min Act: -0.1700
Data Index: 401507 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9852. Min Act: -0.1700
Data Index: 2420511 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9539. Min Act: -0.1700
Data Index: 4993328 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9539. Min Act: -0.1700
Data Index: 5090923 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9539. Min Act: -0.1700
Data Index: 7235921 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.8914. Min Act: -0.1700
Data Index: 4532047 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9227. Min Act: -0.1700
Data Index: 8526551 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9227. Min Act: -0.1700
Data Index: 4240701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9227. Min Act: -0.1700
Data Index: 3159815 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.9227. Min Act: -0.1700
Data Index: 8683882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.8914. Min Act: -0.1700
Data Index: 3105090 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.8914. Min Act: -0.1700
Data Index: 2428464 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.8914. Min Act: -0.1700
Data Index: 3421252 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1727. Min Range: -5.1727
Max Act: 4.8914. Min Act: -0.1699
Data Index: 1828144 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19