Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.9850. Min Act: -0.1700
Data Index: 5317921 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.6567. Min Act: -0.1700
Data Index: 3555678 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.6567. Min Act: -0.1700
Data Index: 3134919 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.6410. Min Act: -0.1700
Data Index: 2261636 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.6410. Min Act: -0.1700
Data Index: 8403454 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.6410. Min Act: -0.1700
Data Index: 4147742 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.6097. Min Act: -0.1700
Data Index: 5522961 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.6097. Min Act: -0.1700
Data Index: 8045137 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.5941. Min Act: -0.1700
Data Index: 2244240 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.5784. Min Act: -0.1700
Data Index: 644065 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.5784. Min Act: -0.1700
Data Index: 3856439 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.5627. Min Act: -0.1700
Data Index: 3632448 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.5471. Min Act: -0.1700
Data Index: 1687092 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.5158. Min Act: -0.1700
Data Index: 8274584 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.5001. Min Act: -0.1700
Data Index: 3382841 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.4844. Min Act: -0.1700
Data Index: 4664524 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.4844. Min Act: -0.1700
Data Index: 2019332 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.4844. Min Act: -0.1700
Data Index: 2707114 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.4688. Min Act: -0.1700
Data Index: 3455651 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9850. Min Range: -3.9850
Max Act: 3.4688. Min Act: -0.1700
Data Index: 6251903 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19