Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2495 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2730. Min Range: -8.2730
Max Act: 8.2730. Min Act: -0.1700
Data Index: 6852999 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2730. Min Range: -8.2730
Max Act: 8.2730. Min Act: -0.1700
Data Index: 1745822 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2730. Min Range: -8.2730
Max Act: 8.0855. Min Act: -0.1700
Data Index: 1832298 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2730. Min Range: -8.2730
Max Act: 8.0230. Min Act: -0.1700
Data Index: 5794476 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2730. Min Range: -8.2730
Max Act: 8.0230. Min Act: -0.1700
Data Index: 2013744 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.8980. Min Act: -0.1700
Data Index: 4055053 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.8355. Min Act: -0.1700
Data Index: 5685575 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.8355. Min Act: -0.1700
Data Index: 4293907 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.8355. Min Act: -0.1700
Data Index: 3781586 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.7730. Min Act: -0.1700
Data Index: 3942708 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.7105. Min Act: -0.1700
Data Index: 2893177 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.7105. Min Act: -0.1700
Data Index: 8093375 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.7730. Min Act: -0.1700
Data Index: 8741805 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.6480. Min Act: -0.1700
Data Index: 6637635 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.5855. Min Act: -0.1700
Data Index: 7728978 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.6480. Min Act: -0.1700
Data Index: 8489429 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.5855. Min Act: -0.1700
Data Index: 3865815 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.5855. Min Act: -0.1700
Data Index: 5776043 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.5855. Min Act: -0.1700
Data Index: 3506008 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2730. Min Range: -8.2730
Max Act: 7.5543. Min Act: -0.1700
Data Index: 5409128 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19