Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0062. Min Range: -6.0062
Max Act: 6.0062. Min Act: -0.1700
Data Index: 6509287 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.7250. Min Act: -0.1700
Data Index: 4399832 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.6937. Min Act: -0.1700
Data Index: 892538 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.6625. Min Act: -0.1700
Data Index: 8500140 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6317868 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.6625. Min Act: -0.1700
Data Index: 7249734 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.6312. Min Act: -0.1700
Data Index: 6478309 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.6312. Min Act: -0.1700
Data Index: 109343 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.6000. Min Act: -0.1700
Data Index: 1520780 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.5687. Min Act: -0.1700
Data Index: 3013505 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.5375. Min Act: -0.1700
Data Index: 4973719 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.4750. Min Act: -0.1700
Data Index: 1995433 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.4750. Min Act: -0.1700
Data Index: 4213490 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.4750. Min Act: -0.1700
Data Index: 2779991 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.4437. Min Act: -0.1700
Data Index: 8639185 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.4125. Min Act: -0.1700
Data Index: 174199 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.4125. Min Act: -0.1700
Data Index: 4643494 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.3812. Min Act: -0.1700
Data Index: 1202064 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.3812. Min Act: -0.1700
Data Index: 5192217 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0062. Min Range: -6.0062
Max Act: 5.3500. Min Act: -0.1700
Data Index: 210777 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19