Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.9935. Min Act: -0.1700
Data Index: 279182 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.6185. Min Act: -0.1700
Data Index: 1796842 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.5247. Min Act: -0.1700
Data Index: 2324017 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.4935. Min Act: -0.1700
Data Index: 7766686 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.5247. Min Act: -0.1700
Data Index: 8066916 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.4935. Min Act: -0.1700
Data Index: 5624337 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.4622. Min Act: -0.1700
Data Index: 3678113 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.4310. Min Act: -0.1700
Data Index: 6275280 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.2747. Min Act: -0.1700
Data Index: 1403236 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.2747. Min Act: -0.1700
Data Index: 2201687 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.2435. Min Act: -0.1700
Data Index: 4450783 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.2747. Min Act: -0.1700
Data Index: 8808886 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.2747. Min Act: -0.1700
Data Index: 4701927 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.1810. Min Act: -0.1700
Data Index: 1458511 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.1810. Min Act: -0.1700
Data Index: 4162341 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.1185. Min Act: -0.1700
Data Index: 115636 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.1497. Min Act: -0.1700
Data Index: 7539548 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.1185. Min Act: -0.1700
Data Index: 1631485 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.1497. Min Act: -0.1700
Data Index: 766365 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9935. Min Range: -7.9935
Max Act: 7.1497. Min Act: -0.1700
Data Index: 4349950 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19