Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5108 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0740. Min Range: -5.0740
Max Act: 5.0427. Min Act: -0.1700
Data Index: 5838654 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0740. Min Range: -5.0740
Max Act: 5.0740. Min Act: -0.1700
Data Index: 6422927 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0740. Min Range: -5.0740
Max Act: 5.0427. Min Act: -0.1700
Data Index: 1108578 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.9490. Min Act: -0.1700
Data Index: 6797960 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.9490. Min Act: -0.1700
Data Index: 6554829 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.8865. Min Act: -0.1700
Data Index: 611423 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.8240. Min Act: -0.1700
Data Index: 4071747 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.8240. Min Act: -0.1700
Data Index: 2660099 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.8240. Min Act: -0.1700
Data Index: 1225978 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.7615. Min Act: -0.1700
Data Index: 5899990 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.7927. Min Act: -0.1700
Data Index: 4565871 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.7615. Min Act: -0.1700
Data Index: 1536413 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.7615. Min Act: -0.1700
Data Index: 121721 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.6990. Min Act: -0.1700
Data Index: 1126047 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.6990. Min Act: -0.1700
Data Index: 3559990 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.6990. Min Act: -0.1700
Data Index: 192329 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.6677. Min Act: -0.1700
Data Index: 3132703 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.6677. Min Act: -0.1700
Data Index: 3649341 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.6677. Min Act: -0.1700
Data Index: 1146519 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0740. Min Range: -5.0740
Max Act: 4.6677. Min Act: -0.1700
Data Index: 6193402 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19