Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.8878. Min Act: -0.1700
Data Index: 2917575 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.8252. Min Act: -0.1700
Data Index: 4414913 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.7627. Min Act: -0.1700
Data Index: 2188696 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6688. Min Act: -0.1700
Data Index: 6452040 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6688. Min Act: -0.1700
Data Index: 2039142 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6688. Min Act: -0.1700
Data Index: 3669512 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6062. Min Act: -0.1700
Data Index: 4414914 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6375. Min Act: -0.1700
Data Index: 738034 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6375. Min Act: -0.1700
Data Index: 5453213 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6375. Min Act: -0.1700
Data Index: 4749318 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6062. Min Act: -0.1700
Data Index: 4906339 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6062. Min Act: -0.1700
Data Index: 7865651 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6062. Min Act: -0.1700
Data Index: 8093446 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.5749. Min Act: -0.1700
Data Index: 3815423 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.5906. Min Act: -0.1700
Data Index: 5252640 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.5749. Min Act: -0.1700
Data Index: 3722517 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.5906. Min Act: -0.1700
Data Index: 1280750 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.6062. Min Act: -0.1700
Data Index: 5497446 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.5906. Min Act: -0.1700
Data Index: 4066683 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8878. Min Range: -3.8878
Max Act: 3.5906. Min Act: -0.1700
Data Index: 649476 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19