Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.5115. Min Act: -0.1700
Data Index: 2599876 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.4802. Min Act: -0.1700
Data Index: 658913 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.1052. Min Act: -0.1700
Data Index: 5599355 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0740. Min Act: -0.1700
Data Index: 2835067 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0740. Min Act: -0.1700
Data Index: 5403931 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0115. Min Act: -0.1700
Data Index: 650110 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.9490. Min Act: -0.1700
Data Index: 2008988 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.8865. Min Act: -0.1700
Data Index: 5366743 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.8865. Min Act: -0.1700
Data Index: 812250 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.8240. Min Act: -0.1700
Data Index: 360859 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.7927. Min Act: -0.1700
Data Index: 4090350 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.7927. Min Act: -0.1700
Data Index: 4309159 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1844611 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.7615. Min Act: -0.1700
Data Index: 1252799 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.7615. Min Act: -0.1700
Data Index: 6634345 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.7615. Min Act: -0.1700
Data Index: 115525 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.7302. Min Act: -0.1700
Data Index: 230862 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.7302. Min Act: -0.1700
Data Index: 1216837 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.6990. Min Act: -0.1700
Data Index: 1407296 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.6990. Min Act: -0.1700
Data Index: 5894555 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19