Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2902 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0748. Min Range: -2.0748
Max Act: 2.0748. Min Act: -0.1700
Data Index: 486259 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0748. Min Range: -2.0748
Max Act: 2.0243. Min Act: -0.1700
Data Index: 5922874 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9736. Min Act: -0.1700
Data Index: 3410156 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9906. Min Act: -0.1700
Data Index: 4255948 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9906. Min Act: -0.1700
Data Index: 3074777 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9567. Min Act: -0.1700
Data Index: 8693590 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9736. Min Act: -0.1700
Data Index: 4383909 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9736. Min Act: -0.1700
Data Index: 7710327 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9736. Min Act: -0.1700
Data Index: 5253710 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9736. Min Act: -0.1700
Data Index: 5488520 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9567. Min Act: -0.1700
Data Index: 2227481 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9567. Min Act: -0.1700
Data Index: 8143413 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9736. Min Act: -0.1700
Data Index: 6846239 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9397. Min Act: -0.1700
Data Index: 1886494 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9397. Min Act: -0.1700
Data Index: 5752139 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9057. Min Act: -0.1700
Data Index: 3865836 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9057. Min Act: -0.1700
Data Index: 7826535 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9057. Min Act: -0.1700
Data Index: 3024738 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.9057. Min Act: -0.1700
Data Index: 6270220 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0748. Min Range: -2.0748
Max Act: 1.8886. Min Act: -0.1700
Data Index: 3985720 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19