Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.5757. Min Act: -0.1700
Data Index: 3750994 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.5444. Min Act: -0.1700
Data Index: 650849 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.4819. Min Act: -0.1700
Data Index: 5087732 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.4819. Min Act: -0.1700
Data Index: 1955037 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.3882. Min Act: -0.1700
Data Index: 1380657 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.3882. Min Act: -0.1700
Data Index: 1861546 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.3569. Min Act: -0.1700
Data Index: 768631 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.2944. Min Act: -0.1700
Data Index: 4170 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.2319. Min Act: -0.1700
Data Index: 5416675 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.2007. Min Act: -0.1700
Data Index: 6275725 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.2007. Min Act: -0.1700
Data Index: 1470346 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.2007. Min Act: -0.1700
Data Index: 4676922 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.2007. Min Act: -0.1700
Data Index: 5124268 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.2007. Min Act: -0.1700
Data Index: 6866108 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.1694. Min Act: -0.1700
Data Index: 65802 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.1694. Min Act: -0.1700
Data Index: 2645408 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.1694. Min Act: -0.1700
Data Index: 6878503 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.1694. Min Act: -0.1700
Data Index: 4786407 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.1381. Min Act: -0.1700
Data Index: 127887 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5757. Min Range: -4.5757
Max Act: 4.1381. Min Act: -0.1700
Data Index: 6635250 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19