Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 312 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.8829. Min Act: -0.1700
Data Index: 4400215 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.8204. Min Act: -0.1700
Data Index: 1816640 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.8516. Min Act: -0.1700
Data Index: 4913851 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.8204. Min Act: -0.1700
Data Index: 4882265 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.8204. Min Act: -0.1700
Data Index: 8397930 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7891. Min Act: -0.1700
Data Index: 8215454 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7891. Min Act: -0.1700
Data Index: 1016708 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7891. Min Act: -0.1700
Data Index: 7909996 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7891. Min Act: -0.1700
Data Index: 7677875 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7891. Min Act: -0.1700
Data Index: 2985143 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.8204. Min Act: -0.1700
Data Index: 5711376 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7891. Min Act: -0.1700
Data Index: 743296 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7578. Min Act: -0.1700
Data Index: 2594846 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7578. Min Act: -0.1700
Data Index: 3883157 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7578. Min Act: -0.1700
Data Index: 4177295 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7578. Min Act: -0.1700
Data Index: 6891207 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7578. Min Act: -0.1700
Data Index: 662012 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7578. Min Act: -0.1700
Data Index: 8191653 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7578. Min Act: -0.1700
Data Index: 6740858 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8829. Min Range: -3.8829
Max Act: 3.7578. Min Act: -0.1700
Data Index: 3602391 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19