Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.6644. Min Act: -0.1700
Data Index: 744423 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.5394. Min Act: -0.1700
Data Index: 5604295 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.4457. Min Act: -0.1700
Data Index: 2303122 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.4457. Min Act: -0.1700
Data Index: 528511 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.3832. Min Act: -0.1700
Data Index: 3414616 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.2582. Min Act: -0.1700
Data Index: 583041 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.2582. Min Act: -0.1700
Data Index: 2477555 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.2269. Min Act: -0.1700
Data Index: 4629627 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.2269. Min Act: -0.1700
Data Index: 4705436 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1957. Min Act: -0.1700
Data Index: 5320602 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1644. Min Act: -0.1700
Data Index: 3411640 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1644. Min Act: -0.1700
Data Index: 885282 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1332. Min Act: -0.1700
Data Index: 5324098 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1644. Min Act: -0.1700
Data Index: 1719547 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1332. Min Act: -0.1700
Data Index: 5861709 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1332. Min Act: -0.1700
Data Index: 7589509 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1332. Min Act: -0.1700
Data Index: 926241 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1332. Min Act: -0.1700
Data Index: 4898500 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1019. Min Act: -0.1700
Data Index: 3652083 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6644. Min Range: -5.6644
Max Act: 5.1019. Min Act: -0.1700
Data Index: 4145186 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19