Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3327 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0727. Min Range: -10.0727
Max Act: 10.0727. Min Act: -0.1700
Data Index: 7336256 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0727. Min Range: -10.0727
Max Act: 9.3227. Min Act: -0.1700
Data Index: 1788766 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0727. Min Range: -10.0727
Max Act: 9.1977. Min Act: -0.1700
Data Index: 8658923 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0727. Min Range: -10.0727
Max Act: 9.1352. Min Act: -0.1700
Data Index: 1788769 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0727. Min Range: -10.0727
Max Act: 9.0727. Min Act: -0.1700
Data Index: 7685137 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0727. Min Range: -10.0727
Max Act: 9.0727. Min Act: -0.1700
Data Index: 5664643 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.9477. Min Act: -0.1700
Data Index: 3054903 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.8852. Min Act: -0.1700
Data Index: 2673339 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.8852. Min Act: -0.1700
Data Index: 7348135 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.8852. Min Act: -0.1700
Data Index: 4370674 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.8227. Min Act: -0.1700
Data Index: 3932254 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.8227. Min Act: -0.1700
Data Index: 12177 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.8227. Min Act: -0.1700
Data Index: 6590209 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.7602. Min Act: -0.1700
Data Index: 4880799 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.7602. Min Act: -0.1700
Data Index: 8196624 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.7602. Min Act: -0.1700
Data Index: 6643940 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.7602. Min Act: -0.1700
Data Index: 3306229 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.6352. Min Act: -0.1700
Data Index: 6202381 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.6352. Min Act: -0.1700
Data Index: 3973515 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0727. Min Range: -10.0727
Max Act: 8.6352. Min Act: -0.1700
Data Index: 6680395 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19