Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4612 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.9655. Min Act: -0.1700
Data Index: 952497 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.6843. Min Act: -0.1700
Data Index: 3084666 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.6218. Min Act: -0.1700
Data Index: 5754629 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.4343. Min Act: -0.1700
Data Index: 1623680 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.3718. Min Act: -0.1700
Data Index: 6430689 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.3718. Min Act: -0.1700
Data Index: 8130163 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.3718. Min Act: -0.1700
Data Index: 945383 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.3405. Min Act: -0.1700
Data Index: 8415963 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.3093. Min Act: -0.1700
Data Index: 4063474 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.3093. Min Act: -0.1700
Data Index: 5114596 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2780. Min Act: -0.1700
Data Index: 3030064 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.3093. Min Act: -0.1700
Data Index: 5031662 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2780. Min Act: -0.1700
Data Index: 5772715 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2780. Min Act: -0.1700
Data Index: 945382 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2780. Min Act: -0.1700
Data Index: 3090400 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2780. Min Act: -0.1700
Data Index: 7684827 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2468. Min Act: -0.1700
Data Index: 2551691 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2468. Min Act: -0.1700
Data Index: 952500 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2155. Min Act: -0.1700
Data Index: 3706459 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9655. Min Range: -7.9655
Max Act: 7.2155. Min Act: -0.1700
Data Index: 5902920 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19