Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.4468. Min Act: -0.1700
Data Index: 5305271 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.4154. Min Act: -0.1700
Data Index: 133975 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.4311. Min Act: -0.1700
Data Index: 1516165 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.3841. Min Act: -0.1700
Data Index: 2125417 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.3684. Min Act: -0.1700
Data Index: 8727301 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.3370. Min Act: -0.1700
Data Index: 3236022 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.3213. Min Act: -0.1700
Data Index: 6242947 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.3213. Min Act: -0.1700
Data Index: 5136305 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.3056. Min Act: -0.1700
Data Index: 3630521 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.3056. Min Act: -0.1700
Data Index: 7696387 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2899. Min Act: -0.1700
Data Index: 6734390 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.3056. Min Act: -0.1700
Data Index: 6961683 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2742. Min Act: -0.1700
Data Index: 2392432 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2899. Min Act: -0.1700
Data Index: 5889799 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2585. Min Act: -0.1700
Data Index: 4275296 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2585. Min Act: -0.1700
Data Index: 8461822 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2742. Min Act: -0.1700
Data Index: 8435880 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2742. Min Act: -0.1700
Data Index: 7903902 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2585. Min Act: -0.1700
Data Index: 7818354 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4468. Min Range: -3.4468
Max Act: 3.2271. Min Act: -0.1700
Data Index: 6849298 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19