Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3090. Min Range: -10.3090
Max Act: 10.3090. Min Act: -0.1700
Data Index: 3886478 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3090. Min Range: -10.3090
Max Act: 10.2465. Min Act: -0.1699
Data Index: 6657220 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3090. Min Range: -10.3090
Max Act: 10.0590. Min Act: -0.1700
Data Index: 2380574 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.9340. Min Act: -0.1700
Data Index: 5189671 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.9340. Min Act: -0.1700
Data Index: 7989793 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.9340. Min Act: -0.1700
Data Index: 6384973 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.9340. Min Act: -0.1700
Data Index: 590457 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.8715. Min Act: -0.1700
Data Index: 4039506 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.8715. Min Act: -0.1700
Data Index: 6292000 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.8715. Min Act: -0.1700
Data Index: 930774 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.8090. Min Act: -0.1700
Data Index: 2427648 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.8090. Min Act: -0.1700
Data Index: 3021295 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.8090. Min Act: -0.1700
Data Index: 7798728 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.7465. Min Act: -0.1700
Data Index: 4347889 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.7465. Min Act: -0.1700
Data Index: 1647603 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.7465. Min Act: -0.1700
Data Index: 7292369 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.7465. Min Act: -0.1700
Data Index: 830636 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.7465. Min Act: -0.1700
Data Index: 5674324 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.6840. Min Act: -0.1700
Data Index: 7747282 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3090. Min Range: -10.3090
Max Act: 9.6840. Min Act: -0.1700
Data Index: 2972900 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19