Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.9984. Min Act: -0.1700
Data Index: 1049558 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.9671. Min Act: -0.1700
Data Index: 8734722 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.9671. Min Act: -0.1700
Data Index: 4152708 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.9046. Min Act: -0.1700
Data Index: 3866703 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.8733. Min Act: -0.1700
Data Index: 7009096 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.8421. Min Act: -0.1700
Data Index: 7382744 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.8108. Min Act: -0.1700
Data Index: 6367738 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7795. Min Act: -0.1700
Data Index: 4902418 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7482. Min Act: -0.1700
Data Index: 2723974 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7795. Min Act: -0.1700
Data Index: 8483825 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7795. Min Act: -0.1700
Data Index: 7659922 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7795. Min Act: -0.1700
Data Index: 5387958 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7795. Min Act: -0.1700
Data Index: 4152709 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7482. Min Act: -0.1700
Data Index: 4152707 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7170. Min Act: -0.1700
Data Index: 2860473 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7482. Min Act: -0.1700
Data Index: 7330001 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7482. Min Act: -0.1700
Data Index: 460178 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7170. Min Act: -0.1700
Data Index: 6691692 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.7170. Min Act: -0.1700
Data Index: 4462383 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9984. Min Range: -3.9984
Max Act: 3.6857. Min Act: -0.1700
Data Index: 1180385 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19