Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1609 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1045. Min Range: -5.1045
Max Act: 5.1045. Min Act: -0.1700
Data Index: 738973 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.6357. Min Act: -0.1700
Data Index: 5402566 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.5732. Min Act: -0.1700
Data Index: 6395897 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.5107. Min Act: -0.1700
Data Index: 2733351 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.4482. Min Act: -0.1700
Data Index: 1809395 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.4482. Min Act: -0.1700
Data Index: 1910532 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.4169. Min Act: -0.1700
Data Index: 7201459 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.4169. Min Act: -0.1700
Data Index: 5830807 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3544. Min Act: -0.1700
Data Index: 6122893 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3544. Min Act: -0.1700
Data Index: 5832899 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3544. Min Act: -0.1700
Data Index: 1077167 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3544. Min Act: -0.1700
Data Index: 677666 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.2919. Min Act: -0.1700
Data Index: 5005594 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3232. Min Act: -0.1700
Data Index: 8447376 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3232. Min Act: -0.1700
Data Index: 7668383 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3232. Min Act: -0.1700
Data Index: 2904301 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3232. Min Act: -0.1700
Data Index: 5460783 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3232. Min Act: -0.1700
Data Index: 7603375 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.3232. Min Act: -0.1700
Data Index: 6133042 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.2919. Min Act: -0.1700
Data Index: 2716968 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19