Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 268 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.4096. Min Act: -0.1700
Data Index: 1856405 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.3783. Min Act: -0.1700
Data Index: 8600848 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.3158. Min Act: -0.1700
Data Index: 8760793 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.2846. Min Act: -0.1700
Data Index: 7019548 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.2846. Min Act: -0.1700
Data Index: 823407 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.2846. Min Act: -0.1700
Data Index: 20325 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.2846. Min Act: -0.1700
Data Index: 1463331 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.2533. Min Act: -0.1700
Data Index: 2654798 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.2533. Min Act: -0.1700
Data Index: 8195895 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1908. Min Act: -0.1700
Data Index: 2877592 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1908. Min Act: -0.1700
Data Index: 2258894 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1908. Min Act: -0.1700
Data Index: 5975870 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1908. Min Act: -0.1700
Data Index: 6063147 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1908. Min Act: -0.1700
Data Index: 1804209 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1908. Min Act: -0.1700
Data Index: 1563781 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1908. Min Act: -0.1700
Data Index: 7385251 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1908. Min Act: -0.1700
Data Index: 4768922 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1596. Min Act: -0.1700
Data Index: 63062 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1596. Min Act: -0.1700
Data Index: 876010 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4096. Min Range: -5.4096
Max Act: 5.1596. Min Act: -0.1700
Data Index: 7495916 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19