Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.8016. Min Act: -0.1700
Data Index: 5492235 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.8328. Min Act: -0.1700
Data Index: 844918 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.6453. Min Act: -0.1700
Data Index: 4980172 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.5516. Min Act: -0.1700
Data Index: 6739764 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.5203. Min Act: -0.1700
Data Index: 8619139 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.4891. Min Act: -0.1700
Data Index: 4238931 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.4891. Min Act: -0.1700
Data Index: 8592130 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.4578. Min Act: -0.1700
Data Index: 5201681 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.4266. Min Act: -0.1700
Data Index: 4747552 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.3953. Min Act: -0.1700
Data Index: 6524534 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.4266. Min Act: -0.1700
Data Index: 5910315 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.4266. Min Act: -0.1700
Data Index: 1416609 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.4266. Min Act: -0.1700
Data Index: 5384548 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.3953. Min Act: -0.1700
Data Index: 6204504 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.3953. Min Act: -0.1700
Data Index: 2386105 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.3953. Min Act: -0.1700
Data Index: 5754516 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.3641. Min Act: -0.1700
Data Index: 2926190 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.3641. Min Act: -0.1700
Data Index: 1012340 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.3328. Min Act: -0.1700
Data Index: 6342918 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8328. Min Range: -5.8328
Max Act: 5.3328. Min Act: -0.1700
Data Index: 8256710 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19