Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1932 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.9816. Min Act: -0.1700
Data Index: 2516768 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.9503. Min Act: -0.1700
Data Index: 1355306 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.8878. Min Act: -0.1700
Data Index: 7920625 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.8878. Min Act: -0.1700
Data Index: 4501796 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.8253. Min Act: -0.1700
Data Index: 4611380 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.7628. Min Act: -0.1700
Data Index: 5909779 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.7628. Min Act: -0.1700
Data Index: 3772112 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.7316. Min Act: -0.1700
Data Index: 206311 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.7628. Min Act: -0.1700
Data Index: 2178357 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.7316. Min Act: -0.1700
Data Index: 2006688 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.7003. Min Act: -0.1700
Data Index: 7638797 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.7003. Min Act: -0.1700
Data Index: 6757106 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.6691. Min Act: -0.1700
Data Index: 4438707 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.6691. Min Act: -0.1700
Data Index: 740807 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.6378. Min Act: -0.1700
Data Index: 7585735 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.6691. Min Act: -0.1700
Data Index: 6864770 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.6066. Min Act: -0.1700
Data Index: 7670436 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.6378. Min Act: -0.1700
Data Index: 7968963 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.6066. Min Act: -0.1700
Data Index: 3998062 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9816. Min Range: -6.9816
Max Act: 6.6066. Min Act: -0.1700
Data Index: 4721213 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19