Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1112 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.2987. Min Act: -0.1700
Data Index: 3393661 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.1737. Min Act: -0.1700
Data Index: 3942920 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.1737. Min Act: -0.1700
Data Index: 3942921 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.1737. Min Act: -0.1700
Data Index: 3393662 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.1112. Min Act: -0.1700
Data Index: 8627183 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.0487. Min Act: -0.1700
Data Index: 7665571 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.1112. Min Act: -0.1700
Data Index: 3393659 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.1112. Min Act: -0.1700
Data Index: 3393660 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2987. Min Range: -9.2987
Max Act: 9.0487. Min Act: -0.1698
Data Index: 97260 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.9862. Min Act: -0.1700
Data Index: 7274557 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.9862. Min Act: -0.1700
Data Index: 3274928 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.9862. Min Act: -0.1700
Data Index: 555296 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.9237. Min Act: -0.1700
Data Index: 7300617 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.9237. Min Act: -0.1700
Data Index: 7672825 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.8612. Min Act: -0.1700
Data Index: 1141542 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.9237. Min Act: -0.1700
Data Index: 3707055 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.8612. Min Act: -0.1700
Data Index: 850900 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.8612. Min Act: -0.1700
Data Index: 6366021 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.8612. Min Act: -0.1700
Data Index: 3633783 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2987. Min Range: -9.2987
Max Act: 8.8612. Min Act: -0.1700
Data Index: 1112990 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19