Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2567 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8988. Min Act: -0.1700
Data Index: 5038633 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8676. Min Act: -0.1700
Data Index: 795916 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8051. Min Act: -0.1700
Data Index: 2436562 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 2618237 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 622280 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6801. Min Act: -0.1700
Data Index: 1089263 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6801. Min Act: -0.1700
Data Index: 4972081 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 453283 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6176. Min Act: -0.1700
Data Index: 7104179 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6176. Min Act: -0.1700
Data Index: 5223603 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5863. Min Act: -0.1700
Data Index: 3950873 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5863. Min Act: -0.1700
Data Index: 1860028 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5863. Min Act: -0.1700
Data Index: 92699 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5551. Min Act: -0.1700
Data Index: 7121302 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5551. Min Act: -0.1700
Data Index: 3080258 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5551. Min Act: -0.1700
Data Index: 1914230 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5551. Min Act: -0.1700
Data Index: 7211542 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5551. Min Act: -0.1700
Data Index: 2188205 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5238. Min Act: -0.1700
Data Index: 2262309 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.5238. Min Act: -0.1700
Data Index: 5037856 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19