Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.9880. Min Act: -0.1700
Data Index: 569344 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.8630. Min Act: -0.1700
Data Index: 1639792 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.8630. Min Act: -0.1700
Data Index: 3222480 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.8317. Min Act: -0.1700
Data Index: 3284004 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.8317. Min Act: -0.1700
Data Index: 3054517 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.7692. Min Act: -0.1700
Data Index: 5549797 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.7067. Min Act: -0.1700
Data Index: 4622876 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.7067. Min Act: -0.1700
Data Index: 7714796 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.7380. Min Act: -0.1700
Data Index: 2863156 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.7380. Min Act: -0.1700
Data Index: 5734567 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.6755. Min Act: -0.1700
Data Index: 5120215 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.7380. Min Act: -0.1700
Data Index: 3409259 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.6755. Min Act: -0.1700
Data Index: 1892949 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.6755. Min Act: -0.1700
Data Index: 6753212 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.6755. Min Act: -0.1700
Data Index: 1577479 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.7067. Min Act: -0.1700
Data Index: 3993890 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.6755. Min Act: -0.1700
Data Index: 1345983 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.6442. Min Act: -0.1700
Data Index: 864648 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.6442. Min Act: -0.1700
Data Index: 4470356 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9880. Min Range: -7.9880
Max Act: 7.6442. Min Act: -0.1700
Data Index: 47463 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19