Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.6462. Min Act: -0.1700
Data Index: 4414034 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.5212. Min Act: -0.1700
Data Index: 5645726 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.5524. Min Act: -0.1700
Data Index: 3919584 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.3962. Min Act: -0.1700
Data Index: 4768316 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.3337. Min Act: -0.1700
Data Index: 5562577 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.2712. Min Act: -0.1700
Data Index: 4601980 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.2399. Min Act: -0.1700
Data Index: 1564685 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.2399. Min Act: -0.1700
Data Index: 472593 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.2087. Min Act: -0.1700
Data Index: 6467019 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.2087. Min Act: -0.1700
Data Index: 4016521 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.1774. Min Act: -0.1700
Data Index: 2764376 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.2087. Min Act: -0.1700
Data Index: 4337211 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.1774. Min Act: -0.1700
Data Index: 3195288 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.1462. Min Act: -0.1700
Data Index: 7859101 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.1149. Min Act: -0.1700
Data Index: 4293464 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.1149. Min Act: -0.1700
Data Index: 8300575 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.1149. Min Act: -0.1700
Data Index: 290877 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.0837. Min Act: -0.1700
Data Index: 7765591 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.0837. Min Act: -0.1700
Data Index: 6447127 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6462. Min Range: -5.6462
Max Act: 5.0524. Min Act: -0.1700
Data Index: 2404283 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19