Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1463. Min Range: -4.1463
Max Act: 4.1463. Min Act: -0.1700
Data Index: 8476226 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.9275. Min Act: -0.1700
Data Index: 3369647 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.7868. Min Act: -0.1700
Data Index: 7999053 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.7711. Min Act: -0.1700
Data Index: 7493008 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.7711. Min Act: -0.1700
Data Index: 2386039 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.7242. Min Act: -0.1700
Data Index: 3862688 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.7086. Min Act: -0.1700
Data Index: 6519289 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.7086. Min Act: -0.1700
Data Index: 8405266 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6929. Min Act: -0.1700
Data Index: 8030733 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6773. Min Act: -0.1700
Data Index: 3919733 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6929. Min Act: -0.1700
Data Index: 2456940 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6616. Min Act: -0.1700
Data Index: 6376586 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6616. Min Act: -0.1700
Data Index: 4064050 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6773. Min Act: -0.1700
Data Index: 5743401 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6616. Min Act: -0.1700
Data Index: 8317372 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6460. Min Act: -0.1700
Data Index: 2138581 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6304. Min Act: -0.1700
Data Index: 6345844 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6460. Min Act: -0.1700
Data Index: 4763679 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6304. Min Act: -0.1700
Data Index: 8336653 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1463. Min Range: -4.1463
Max Act: 3.6147. Min Act: -0.1700
Data Index: 5526675 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19