Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4450 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.9896. Min Act: -0.1700
Data Index: 5024501 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.6771. Min Act: -0.1700
Data Index: 169934 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.4896. Min Act: -0.1700
Data Index: 7879800 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.4896. Min Act: -0.1700
Data Index: 6115783 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.4271. Min Act: -0.1700
Data Index: 427663 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.4271. Min Act: -0.1700
Data Index: 2336929 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.4271. Min Act: -0.1700
Data Index: 2510028 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.2396. Min Act: -0.1700
Data Index: 8022884 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.2396. Min Act: -0.1700
Data Index: 7148765 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.2396. Min Act: -0.1700
Data Index: 5169680 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.2396. Min Act: -0.1700
Data Index: 2438047 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.1146. Min Act: -0.1700
Data Index: 4325478 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.1146. Min Act: -0.1700
Data Index: 4467093 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.1146. Min Act: -0.1700
Data Index: 2183201 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.1146. Min Act: -0.1700
Data Index: 3501471 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.1146. Min Act: -0.1700
Data Index: 1887931 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.0521. Min Act: -0.1700
Data Index: 2615301 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.0521. Min Act: -0.1700
Data Index: 5406233 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.0521. Min Act: -0.1700
Data Index: 5682106 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.9896. Min Range: -14.9896
Max Act: 14.0521. Min Act: -0.1700
Data Index: 97592 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19