Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4923 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1815. Min Range: -4.1815
Max Act: 4.1815. Min Act: -0.1700
Data Index: 8234950 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1815. Min Range: -4.1815
Max Act: 4.0252. Min Act: -0.1700
Data Index: 7934913 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1815. Min Range: -4.1815
Max Act: 4.0252. Min Act: -0.1700
Data Index: 8234951 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.9939. Min Act: -0.1700
Data Index: 6096067 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.9314. Min Act: -0.1700
Data Index: 7471359 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.9002. Min Act: -0.1700
Data Index: 2433458 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.9002. Min Act: -0.1700
Data Index: 5612479 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.9002. Min Act: -0.1700
Data Index: 4531738 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.8689. Min Act: -0.1700
Data Index: 8158246 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.8689. Min Act: -0.1700
Data Index: 5414579 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.9002. Min Act: -0.1700
Data Index: 1460076 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.8689. Min Act: -0.1700
Data Index: 8472525 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.8063. Min Act: -0.1700
Data Index: 8262507 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.8376. Min Act: -0.1700
Data Index: 1616586 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.8376. Min Act: -0.1700
Data Index: 2835314 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.8063. Min Act: -0.1700
Data Index: 3544197 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.8063. Min Act: -0.1700
Data Index: 4349968 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.7907. Min Act: -0.1700
Data Index: 4132728 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.7907. Min Act: -0.1700
Data Index: 472757 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1815. Min Range: -4.1815
Max Act: 3.7594. Min Act: -0.1700
Data Index: 4481112 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19