Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 346 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1061. Min Range: -6.1061
Max Act: 6.1061. Min Act: -0.1700
Data Index: 5285624 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.8561. Min Act: -0.1700
Data Index: 4748657 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.7936. Min Act: -0.1700
Data Index: 3982875 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.8249. Min Act: -0.1700
Data Index: 4881833 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.7936. Min Act: -0.1700
Data Index: 2632230 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.7624. Min Act: -0.1700
Data Index: 1853405 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.7936. Min Act: -0.1700
Data Index: 4662663 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.7624. Min Act: -0.1700
Data Index: 8631457 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6686. Min Act: -0.1700
Data Index: 8069612 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6999. Min Act: -0.1700
Data Index: 6595111 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6686. Min Act: -0.1700
Data Index: 6187346 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6686. Min Act: -0.1700
Data Index: 4141406 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6686. Min Act: -0.1700
Data Index: 1976126 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6374. Min Act: -0.1700
Data Index: 3039120 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6061. Min Act: -0.1700
Data Index: 5768504 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6374. Min Act: -0.1700
Data Index: 5139870 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6374. Min Act: -0.1700
Data Index: 2431290 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6686. Min Act: -0.1700
Data Index: 4520257 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6374. Min Act: -0.1700
Data Index: 5746884 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1061. Min Range: -6.1061
Max Act: 5.6374. Min Act: -0.1700
Data Index: 5542999 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19