Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2546 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.4271. Min Act: -0.1700
Data Index: 6160415 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.3333. Min Act: -0.1700
Data Index: 6762032 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.3021. Min Act: -0.1700
Data Index: 7309637 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.3021. Min Act: -0.1700
Data Index: 3872440 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.2708. Min Act: -0.1700
Data Index: 1136434 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.2396. Min Act: -0.1700
Data Index: 4260470 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.2396. Min Act: -0.1700
Data Index: 6655634 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.1771. Min Act: -0.1700
Data Index: 4392157 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.1458. Min Act: -0.1700
Data Index: 1172552 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.1458. Min Act: -0.1700
Data Index: 456604 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.1458. Min Act: -0.1700
Data Index: 6882158 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.1458. Min Act: -0.1700
Data Index: 8368712 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.1146. Min Act: -0.1700
Data Index: 8545764 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0833. Min Act: -0.1700
Data Index: 1924021 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0833. Min Act: -0.1700
Data Index: 956170 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0833. Min Act: -0.1700
Data Index: 4363929 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0521. Min Act: -0.1700
Data Index: 6071664 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0208. Min Act: -0.1700
Data Index: 7080170 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0208. Min Act: -0.1700
Data Index: 8252973 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0208. Min Act: -0.1700
Data Index: 7004213 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19