Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.1661. Min Act: -0.1700
Data Index: 3941971 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.1349. Min Act: -0.1700
Data Index: 3279617 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.1036. Min Act: -0.1700
Data Index: 3667262 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0724. Min Act: -0.1700
Data Index: 3007647 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0724. Min Act: -0.1700
Data Index: 1464225 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0724. Min Act: -0.1700
Data Index: 2502493 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0724. Min Act: -0.1700
Data Index: 8485342 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0411. Min Act: -0.1700
Data Index: 500279 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0724. Min Act: -0.1700
Data Index: 2048387 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 7763383 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 2599607 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3540245 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 8445963 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3898447 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3972764 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 2328769 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 2947117 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1661. Min Range: -5.1661
Max Act: 5.0099. Min Act: -0.1700
Data Index: 2615354 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1661. Min Range: -5.1661
Max Act: 4.9786. Min Act: -0.1700
Data Index: 3620775 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1661. Min Range: -5.1661
Max Act: 4.9786. Min Act: -0.1700
Data Index: 1369497 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19