Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.5185. Min Act: -0.1700
Data Index: 6399757 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.4699. Min Act: -0.1700
Data Index: 795854 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.4211. Min Act: -0.1700
Data Index: 5241272 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.4048. Min Act: -0.1700
Data Index: 6359387 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3558. Min Act: -0.1700
Data Index: 3109714 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3558. Min Act: -0.1700
Data Index: 4198206 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3394. Min Act: -0.1700
Data Index: 7867702 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3230. Min Act: -0.1700
Data Index: 8149070 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3394. Min Act: -0.1700
Data Index: 5148271 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3394. Min Act: -0.1700
Data Index: 5428352 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3230. Min Act: -0.1700
Data Index: 455939 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3230. Min Act: -0.1700
Data Index: 1744008 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.3065. Min Act: -0.1700
Data Index: 2270945 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.2901. Min Act: -0.1700
Data Index: 2552746 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.2901. Min Act: -0.1700
Data Index: 2104087 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.2736. Min Act: -0.1700
Data Index: 5462004 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.2736. Min Act: -0.1700
Data Index: 3500053 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.2736. Min Act: -0.1700
Data Index: 6913421 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.2736. Min Act: -0.1700
Data Index: 961953 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5185. Min Range: -2.5185
Max Act: 2.2736. Min Act: -0.1700
Data Index: 1118696 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19