Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.8357. Min Act: -0.1700
Data Index: 816512 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.8357. Min Act: -0.1700
Data Index: 538040 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.8357. Min Act: -0.1700
Data Index: 4981185 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.8045. Min Act: -0.1700
Data Index: 2467516 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.8045. Min Act: -0.1700
Data Index: 4553929 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7732. Min Act: -0.1700
Data Index: 6625892 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7732. Min Act: -0.1700
Data Index: 6687831 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.8045. Min Act: -0.1700
Data Index: 214521 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.8045. Min Act: -0.1700
Data Index: 908612 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7732. Min Act: -0.1700
Data Index: 3035932 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7420. Min Act: -0.1700
Data Index: 5663396 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7420. Min Act: -0.1700
Data Index: 8647435 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2744758 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7420. Min Act: -0.1700
Data Index: 5343116 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7107. Min Act: -0.1700
Data Index: 7953318 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7107. Min Act: -0.1700
Data Index: 7830572 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7107. Min Act: -0.1700
Data Index: 8469860 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2247239 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2141901 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2162782 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19