Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0672. Min Range: -6.0672
Max Act: 6.0672. Min Act: -0.1700
Data Index: 4646790 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.9422. Min Act: -0.1700
Data Index: 1772463 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.9734. Min Act: -0.1700
Data Index: 7864070 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.8797. Min Act: -0.1700
Data Index: 1232695 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.9109. Min Act: -0.1700
Data Index: 8621144 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.9109. Min Act: -0.1700
Data Index: 6521727 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.9422. Min Act: -0.1700
Data Index: 8136532 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.8797. Min Act: -0.1700
Data Index: 4235667 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.8797. Min Act: -0.1700
Data Index: 7722662 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.8172. Min Act: -0.1700
Data Index: 2512440 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.8484. Min Act: -0.1700
Data Index: 4639029 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.7859. Min Act: -0.1700
Data Index: 7122795 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.8172. Min Act: -0.1700
Data Index: 7771768 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.7859. Min Act: -0.1700
Data Index: 4504616 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.8484. Min Act: -0.1700
Data Index: 209114 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.7859. Min Act: -0.1700
Data Index: 403040 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.7859. Min Act: -0.1700
Data Index: 7722669 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.7859. Min Act: -0.1700
Data Index: 2663758 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.7547. Min Act: -0.1700
Data Index: 4204316 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0672. Min Range: -6.0672
Max Act: 5.7234. Min Act: -0.1700
Data Index: 2012289 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19