Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 131 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2754. Min Range: -6.2754
Max Act: 6.2754. Min Act: -0.1700
Data Index: 5850776 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2754. Min Range: -6.2754
Max Act: 6.1504. Min Act: -0.1700
Data Index: 5954083 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2754. Min Range: -6.2754
Max Act: 6.0879. Min Act: -0.1700
Data Index: 198951 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.9942. Min Act: -0.1700
Data Index: 2031715 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.9629. Min Act: -0.1700
Data Index: 7307029 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.9629. Min Act: -0.1700
Data Index: 5296206 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.9317. Min Act: -0.1700
Data Index: 8559662 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.9317. Min Act: -0.1700
Data Index: 726423 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.9629. Min Act: -0.1700
Data Index: 941409 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.9004. Min Act: -0.1700
Data Index: 8794119 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.9004. Min Act: -0.1700
Data Index: 4263199 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.8379. Min Act: -0.1700
Data Index: 566039 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.8067. Min Act: -0.1700
Data Index: 4644313 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.8067. Min Act: -0.1700
Data Index: 4640080 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.7754. Min Act: -0.1700
Data Index: 2100654 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.7754. Min Act: -0.1700
Data Index: 2127879 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.7754. Min Act: -0.1700
Data Index: 3124901 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.7754. Min Act: -0.1700
Data Index: 2711487 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.7754. Min Act: -0.1700
Data Index: 5990943 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2754. Min Range: -6.2754
Max Act: 5.7754. Min Act: -0.1700
Data Index: 6223307 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19