Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5022 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.9878. Min Act: -0.1700
Data Index: 8498306 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.9369. Min Act: -0.1700
Data Index: 2625634 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.9029. Min Act: -0.1700
Data Index: 8402956 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8858. Min Act: -0.1700
Data Index: 6703757 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8858. Min Act: -0.1700
Data Index: 5863363 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8516. Min Act: -0.1700
Data Index: 524797 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8516. Min Act: -0.1700
Data Index: 4912713 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8516. Min Act: -0.1700
Data Index: 5989882 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8345. Min Act: -0.1700
Data Index: 8116252 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8345. Min Act: -0.1700
Data Index: 621676 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8516. Min Act: -0.1700
Data Index: 4183060 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8345. Min Act: -0.1700
Data Index: 6031709 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8345. Min Act: -0.1700
Data Index: 5822710 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8345. Min Act: -0.1700
Data Index: 3640679 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8173. Min Act: -0.1700
Data Index: 6495083 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8345. Min Act: -0.1700
Data Index: 1831438 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8173. Min Act: -0.1700
Data Index: 524794 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8173. Min Act: -0.1700
Data Index: 739104 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8345. Min Act: -0.1700
Data Index: 4560459 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9878. Min Range: -1.9878
Max Act: 1.8173. Min Act: -0.1700
Data Index: 2699602 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19