Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1615 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.5920. Min Act: -0.1700
Data Index: 1603022 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.3420. Min Act: -0.1700
Data Index: 2922756 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.2170. Min Act: -0.1700
Data Index: 339812 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.2170. Min Act: -0.1700
Data Index: 7399011 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.1858. Min Act: -0.1700
Data Index: 4136247 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.1858. Min Act: -0.1700
Data Index: 2001773 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.0295. Min Act: -0.1700
Data Index: 3389744 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.0295. Min Act: -0.1700
Data Index: 486957 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.0295. Min Act: -0.1700
Data Index: 7394540 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.0295. Min Act: -0.1700
Data Index: 4224721 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5920. Min Range: -5.5920
Max Act: 5.0295. Min Act: -0.1700
Data Index: 2309901 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9983. Min Act: -0.1700
Data Index: 2922755 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9983. Min Act: -0.1700
Data Index: 3134180 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9983. Min Act: -0.1700
Data Index: 8430356 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9670. Min Act: -0.1700
Data Index: 486960 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9670. Min Act: -0.1700
Data Index: 3938155 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9358. Min Act: -0.1700
Data Index: 5581950 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9670. Min Act: -0.1700
Data Index: 6691168 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9358. Min Act: -0.1700
Data Index: 1062029 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5920. Min Range: -5.5920
Max Act: 4.9358. Min Act: -0.1700
Data Index: 6212311 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19