Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2727. Min Range: -3.2727
Max Act: 3.2727. Min Act: -0.1700
Data Index: 7899274 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2727. Min Range: -3.2727
Max Act: 3.1470. Min Act: -0.1700
Data Index: 6577139 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2727. Min Range: -3.2727
Max Act: 3.0682. Min Act: -0.1700
Data Index: 714482 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2727. Min Range: -3.2727
Max Act: 3.0682. Min Act: -0.1700
Data Index: 7095361 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2727. Min Range: -3.2727
Max Act: 3.0524. Min Act: -0.1700
Data Index: 7270307 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2727. Min Range: -3.2727
Max Act: 3.0524. Min Act: -0.1700
Data Index: 7845176 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9892. Min Act: -0.1700
Data Index: 4541611 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2727. Min Range: -3.2727
Max Act: 3.0050. Min Act: -0.1700
Data Index: 2704107 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9892. Min Act: -0.1700
Data Index: 399819 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9892. Min Act: -0.1700
Data Index: 8435009 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9892. Min Act: -0.1700
Data Index: 8687718 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9734. Min Act: -0.1700
Data Index: 923337 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9734. Min Act: -0.1700
Data Index: 34791 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9734. Min Act: -0.1700
Data Index: 6242607 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9892. Min Act: -0.1700
Data Index: 1454578 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9576. Min Act: -0.1700
Data Index: 7187829 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9576. Min Act: -0.1700
Data Index: 8567699 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9417. Min Act: -0.1700
Data Index: 5331533 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9417. Min Act: -0.1700
Data Index: 6921357 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2727. Min Range: -3.2727
Max Act: 2.9417. Min Act: -0.1700
Data Index: 90018 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19