Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.7258. Min Act: -0.1700
Data Index: 4968805 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5693. Min Act: -0.1700
Data Index: 2926784 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.6006. Min Act: -0.1700
Data Index: 7492459 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5067. Min Act: -0.1700
Data Index: 6999093 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5380. Min Act: -0.1700
Data Index: 1526133 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5067. Min Act: -0.1700
Data Index: 2270667 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5067. Min Act: -0.1700
Data Index: 6177729 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5380. Min Act: -0.1700
Data Index: 779486 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4910. Min Act: -0.1700
Data Index: 2148009 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4910. Min Act: -0.1700
Data Index: 7041667 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 300316 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 2494126 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 6641533 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 4204663 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 50013 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 1155288 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 5943543 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 7891757 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 4349470 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4597. Min Act: -0.1700
Data Index: 905238 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19