Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.9056. Min Act: -0.1700
Data Index: 6259254 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.8118. Min Act: -0.1700
Data Index: 2850661 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.7493. Min Act: -0.1700
Data Index: 2025257 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.5306. Min Act: -0.1700
Data Index: 1265515 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.4993. Min Act: -0.1700
Data Index: 302469 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.4993. Min Act: -0.1700
Data Index: 3964933 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.4681. Min Act: -0.1700
Data Index: 640353 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.4681. Min Act: -0.1700
Data Index: 3222682 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.4056. Min Act: -0.1700
Data Index: 3545493 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.2806. Min Act: -0.1700
Data Index: 8615720 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.2493. Min Act: -0.1700
Data Index: 6906713 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.2493. Min Act: -0.1700
Data Index: 5935326 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.1868. Min Act: -0.1700
Data Index: 2175191 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.1868. Min Act: -0.1700
Data Index: 6025388 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.2181. Min Act: -0.1700
Data Index: 8445422 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.1243. Min Act: -0.1700
Data Index: 5684306 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.1556. Min Act: -0.1700
Data Index: 2396662 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.1556. Min Act: -0.1700
Data Index: 7462612 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.1243. Min Act: -0.1700
Data Index: 4171677 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9056. Min Range: -6.9056
Max Act: 6.1243. Min Act: -0.1700
Data Index: 4703289 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19