Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4360 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.2659. Min Act: -0.1700
Data Index: 180059 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.1602. Min Act: -0.1700
Data Index: 7370259 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.1602. Min Act: -0.1700
Data Index: 8501762 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.1427. Min Act: -0.1700
Data Index: 4277659 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.1251. Min Act: -0.1700
Data Index: 7087072 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0901. Min Act: -0.1700
Data Index: 8776096 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0726. Min Act: -0.1700
Data Index: 64075 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0901. Min Act: -0.1700
Data Index: 8234448 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0901. Min Act: -0.1700
Data Index: 6928553 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0551. Min Act: -0.1699
Data Index: 2811908 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0551. Min Act: -0.1700
Data Index: 4247853 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0551. Min Act: -0.1700
Data Index: 5689349 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0377. Min Act: -0.1700
Data Index: 2899494 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0551. Min Act: -0.1700
Data Index: 3117920 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0377. Min Act: -0.1700
Data Index: 2921822 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0377. Min Act: -0.1700
Data Index: 7978716 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0377. Min Act: -0.1700
Data Index: 6847655 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0290. Min Act: -0.1700
Data Index: 4961232 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0377. Min Act: -0.1700
Data Index: 7160047 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2659. Min Range: -1.2659
Max Act: 1.0290. Min Act: -0.1700
Data Index: 6597694 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19