Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1823. Min Range: -6.1823
Max Act: 6.1823. Min Act: -0.1700
Data Index: 6795823 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1823. Min Range: -6.1823
Max Act: 6.1198. Min Act: -0.1700
Data Index: 426430 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1823. Min Range: -6.1823
Max Act: 6.0573. Min Act: -0.1700
Data Index: 5318023 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.9011. Min Act: -0.1700
Data Index: 2307838 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8698. Min Act: -0.1700
Data Index: 280393 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8698. Min Act: -0.1700
Data Index: 7104531 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8386. Min Act: -0.1700
Data Index: 4416526 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8386. Min Act: -0.1700
Data Index: 6467316 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8386. Min Act: -0.1700
Data Index: 2135759 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8386. Min Act: -0.1700
Data Index: 3374970 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8386. Min Act: -0.1700
Data Index: 3634390 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.7761. Min Act: -0.1700
Data Index: 5112627 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8073. Min Act: -0.1700
Data Index: 393082 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8073. Min Act: -0.1700
Data Index: 8761156 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8073. Min Act: -0.1700
Data Index: 2236849 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.7761. Min Act: -0.1700
Data Index: 3750552 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.8073. Min Act: -0.1700
Data Index: 5303135 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.7761. Min Act: -0.1700
Data Index: 353143 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.7136. Min Act: -0.1700
Data Index: 5414631 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1823. Min Range: -6.1823
Max Act: 5.7448. Min Act: -0.1700
Data Index: 5775528 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19