Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0415. Min Range: -4.0415
Max Act: 4.0415. Min Act: -0.1700
Data Index: 5920624 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.9790. Min Act: -0.1700
Data Index: 3962074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.7914. Min Act: -0.1700
Data Index: 3627329 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.7601. Min Act: -0.1700
Data Index: 5791472 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.7288. Min Act: -0.1700
Data Index: 68860 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.7288. Min Act: -0.1700
Data Index: 2349032 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.6975. Min Act: -0.1700
Data Index: 4492062 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.6663. Min Act: -0.1700
Data Index: 3216125 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.6663. Min Act: -0.1700
Data Index: 2154572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.6350. Min Act: -0.1700
Data Index: 8414396 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.6037. Min Act: -0.1700
Data Index: 3739135 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.6037. Min Act: -0.1700
Data Index: 132542 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.6037. Min Act: -0.1700
Data Index: 1585207 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.5880. Min Act: -0.1700
Data Index: 3316801 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.5880. Min Act: -0.1700
Data Index: 5194512 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.6037. Min Act: -0.1700
Data Index: 4531646 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.5880. Min Act: -0.1700
Data Index: 4908942 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.5724. Min Act: -0.1700
Data Index: 1606360 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.5724. Min Act: -0.1700
Data Index: 2382012 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.5724. Min Act: -0.1700
Data Index: 674609 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19