Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.6938. Min Act: -0.1700
Data Index: 3141859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.6625. Min Act: -0.1700
Data Index: 8464129 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.6625. Min Act: -0.1700
Data Index: 4513267 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.6938. Min Act: -0.1700
Data Index: 6908981 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.6312. Min Act: -0.1700
Data Index: 5030783 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5999. Min Act: -0.1700
Data Index: 7593055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5999. Min Act: -0.1700
Data Index: 944803 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5686. Min Act: -0.1700
Data Index: 1169570 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5686. Min Act: -0.1700
Data Index: 4397636 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5686. Min Act: -0.1700
Data Index: 4687015 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 8060602 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 2772822 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 7195634 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 2412696 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 940890 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 6921416 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 2148027 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 5538986 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5060. Min Act: -0.1700
Data Index: 750405 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6938. Min Range: -3.6938
Max Act: 3.5373. Min Act: -0.1700
Data Index: 3994488 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19