Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4446 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.3058. Min Act: -0.1700
Data Index: 1869662 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.3058. Min Act: -0.1700
Data Index: 679465 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.2120. Min Act: -0.1700
Data Index: 8117318 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.1808. Min Act: -0.1700
Data Index: 3192677 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.0558. Min Act: -0.1700
Data Index: 8001622 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.0558. Min Act: -0.1700
Data Index: 610410 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.0245. Min Act: -0.1700
Data Index: 6107899 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.0558. Min Act: -0.1700
Data Index: 4824829 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.0245. Min Act: -0.1700
Data Index: 2334421 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9933. Min Act: -0.1700
Data Index: 5576622 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3058. Min Range: -5.3058
Max Act: 5.0245. Min Act: -0.1700
Data Index: 1265224 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9933. Min Act: -0.1700
Data Index: 5937996 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9933. Min Act: -0.1700
Data Index: 3936198 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9933. Min Act: -0.1700
Data Index: 3933624 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9933. Min Act: -0.1700
Data Index: 7183654 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9620. Min Act: -0.1700
Data Index: 7532828 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9933. Min Act: -0.1700
Data Index: 6724304 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9933. Min Act: -0.1700
Data Index: 1018817 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9620. Min Act: -0.1700
Data Index: 6208878 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3058. Min Range: -5.3058
Max Act: 4.9620. Min Act: -0.1700
Data Index: 2827660 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19