Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4518 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.6428. Min Act: -0.1700
Data Index: 2799687 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.6428. Min Act: -0.1700
Data Index: 1093944 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.5491. Min Act: -0.1700
Data Index: 4433643 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.5491. Min Act: -0.1700
Data Index: 7169059 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.5178. Min Act: -0.1700
Data Index: 980738 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.5178. Min Act: -0.1700
Data Index: 1822027 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.4866. Min Act: -0.1700
Data Index: 5878479 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.4553. Min Act: -0.1700
Data Index: 980737 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.4241. Min Act: -0.1700
Data Index: 2730958 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.4241. Min Act: -0.1700
Data Index: 4541855 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.4241. Min Act: -0.1700
Data Index: 1925312 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.4241. Min Act: -0.1700
Data Index: 2432306 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.3928. Min Act: -0.1700
Data Index: 594249 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.3616. Min Act: -0.1700
Data Index: 1727073 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.2991. Min Act: -0.1700
Data Index: 6317354 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.2991. Min Act: -0.1700
Data Index: 7199150 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.2678. Min Act: -0.1700
Data Index: 227615 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.2991. Min Act: -0.1700
Data Index: 5079639 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.2991. Min Act: -0.1700
Data Index: 7632714 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6428. Min Range: -5.6428
Max Act: 5.2678. Min Act: -0.1700
Data Index: 1669438 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19