Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5070 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.8727. Min Act: -0.1700
Data Index: 5890921 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.6852. Min Act: -0.1700
Data Index: 3895059 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3727. Min Act: -0.1700
Data Index: 8182108 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3727. Min Act: -0.1700
Data Index: 3678069 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3414. Min Act: -0.1700
Data Index: 8042706 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3414. Min Act: -0.1700
Data Index: 6125481 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3414. Min Act: -0.1700
Data Index: 8823923 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3102. Min Act: -0.1700
Data Index: 1301122 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3102. Min Act: -0.1700
Data Index: 7198930 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3102. Min Act: -0.1700
Data Index: 7460349 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.3102. Min Act: -0.1700
Data Index: 3597788 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2789. Min Act: -0.1700
Data Index: 3506403 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2789. Min Act: -0.1700
Data Index: 6153894 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2789. Min Act: -0.1700
Data Index: 558940 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2477. Min Act: -0.1700
Data Index: 3252541 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2477. Min Act: -0.1700
Data Index: 1951853 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2789. Min Act: -0.1700
Data Index: 6090624 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2477. Min Act: -0.1700
Data Index: 4856013 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2164. Min Act: -0.1700
Data Index: 2066993 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8727. Min Range: -5.8727
Max Act: 5.2164. Min Act: -0.1700
Data Index: 2107010 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19