Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3995 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1453. Min Range: -8.1453
Max Act: 8.1453. Min Act: -0.1700
Data Index: 5407073 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.7391. Min Act: -0.1700
Data Index: 5279708 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.7078. Min Act: -0.1700
Data Index: 4835838 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.6453. Min Act: -0.1700
Data Index: 5280822 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.6141. Min Act: -0.1700
Data Index: 6415790 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.6141. Min Act: -0.1700
Data Index: 8763217 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.5828. Min Act: -0.1700
Data Index: 433579 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.5828. Min Act: -0.1700
Data Index: 7189106 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.4891. Min Act: -0.1700
Data Index: 2020693 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.4578. Min Act: -0.1700
Data Index: 621292 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.4891. Min Act: -0.1700
Data Index: 2526768 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.4266. Min Act: -0.1700
Data Index: 5375172 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.3953. Min Act: -0.1700
Data Index: 326370 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.3953. Min Act: -0.1700
Data Index: 2631650 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.3953. Min Act: -0.1700
Data Index: 1621305 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.3328. Min Act: -0.1700
Data Index: 3423667 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.3328. Min Act: -0.1700
Data Index: 5742236 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.3953. Min Act: -0.1700
Data Index: 6317089 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.3641. Min Act: -0.1700
Data Index: 6698522 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1453. Min Range: -8.1453
Max Act: 7.3641. Min Act: -0.1700
Data Index: 3772589 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19