Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.5150. Min Act: -0.1700
Data Index: 5077317 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.5463. Min Act: -0.1700
Data Index: 7438267 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.3900. Min Act: -0.1700
Data Index: 4793421 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.3588. Min Act: -0.1700
Data Index: 3612174 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.1713. Min Act: -0.1700
Data Index: 3756906 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.1400. Min Act: -0.1700
Data Index: 1817434 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.1088. Min Act: -0.1700
Data Index: 3128971 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.1088. Min Act: -0.1700
Data Index: 5494834 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.0463. Min Act: -0.1700
Data Index: 6507224 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.0775. Min Act: -0.1700
Data Index: 2397775 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.0463. Min Act: -0.1700
Data Index: 6415822 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.0150. Min Act: -0.1700
Data Index: 315916 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.0150. Min Act: -0.1700
Data Index: 4254101 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5463. Min Range: -5.5463
Max Act: 5.0150. Min Act: -0.1700
Data Index: 6293114 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5463. Min Range: -5.5463
Max Act: 4.9838. Min Act: -0.1700
Data Index: 2990515 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5463. Min Range: -5.5463
Max Act: 4.9838. Min Act: -0.1700
Data Index: 2665830 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5463. Min Range: -5.5463
Max Act: 4.9838. Min Act: -0.1700
Data Index: 7053980 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5463. Min Range: -5.5463
Max Act: 4.9525. Min Act: -0.1700
Data Index: 8199564 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5463. Min Range: -5.5463
Max Act: 4.9213. Min Act: -0.1700
Data Index: 7443160 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5463. Min Range: -5.5463
Max Act: 4.9213. Min Act: -0.1700
Data Index: 3988863 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19