Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.3063. Min Act: -0.1700
Data Index: 3976059 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.3063. Min Act: -0.1700
Data Index: 1987743 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.2906. Min Act: -0.1700
Data Index: 6943495 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.2749. Min Act: -0.1700
Data Index: 1363925 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.2592. Min Act: -0.1700
Data Index: 1180096 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.2592. Min Act: -0.1700
Data Index: 6398110 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.2278. Min Act: -0.1700
Data Index: 8427616 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.2278. Min Act: -0.1700
Data Index: 8616972 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.2278. Min Act: -0.1700
Data Index: 4279544 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1963. Min Act: -0.1700
Data Index: 1249527 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1806. Min Act: -0.1700
Data Index: 1744415 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1963. Min Act: -0.1700
Data Index: 4968086 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1649. Min Act: -0.1700
Data Index: 1592269 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1649. Min Act: -0.1700
Data Index: 3765280 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1649. Min Act: -0.1700
Data Index: 7500687 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1649. Min Act: -0.1700
Data Index: 3533922 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1491. Min Act: -0.1700
Data Index: 5287650 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1491. Min Act: -0.1700
Data Index: 3369633 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1649. Min Act: -0.1700
Data Index: 2780247 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3063. Min Range: -3.3063
Max Act: 3.1491. Min Act: -0.1700
Data Index: 7370818 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19