Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.8170. Min Act: -0.1700
Data Index: 6102733 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.8170. Min Act: -0.1700
Data Index: 1121645 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.7545. Min Act: -0.1700
Data Index: 2127313 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.6295. Min Act: -0.1700
Data Index: 1124603 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.6295. Min Act: -0.1700
Data Index: 1127727 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.4420. Min Act: -0.1700
Data Index: 7480372 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.3795. Min Act: -0.1700
Data Index: 4133718 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.3170. Min Act: -0.1700
Data Index: 6556898 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.3170. Min Act: -0.1700
Data Index: 2212991 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.2545. Min Act: -0.1700
Data Index: 1014080 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.2545. Min Act: -0.1700
Data Index: 5456716 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.2545. Min Act: -0.1700
Data Index: 3487364 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.1920. Min Act: -0.1700
Data Index: 874093 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.1920. Min Act: -0.1700
Data Index: 4496715 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.1920. Min Act: -0.1700
Data Index: 7769404 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.1920. Min Act: -0.1700
Data Index: 7309424 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.1295. Min Act: -0.1700
Data Index: 1980239 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.1295. Min Act: -0.1700
Data Index: 7565136 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.0670. Min Act: -0.1700
Data Index: 5902436 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8170. Min Range: -10.8170
Max Act: 10.1295. Min Act: -0.1700
Data Index: 1054829 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19