Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1799 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.4708. Min Act: -0.1700
Data Index: 2066889 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.1583. Min Act: -0.1700
Data Index: 1558259 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.1583. Min Act: -0.1700
Data Index: 1951981 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.1270. Min Act: -0.1700
Data Index: 1474477 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.1270. Min Act: -0.1700
Data Index: 1689060 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0645. Min Act: -0.1700
Data Index: 4422375 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0645. Min Act: -0.1700
Data Index: 2548775 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0333. Min Act: -0.1700
Data Index: 100972 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0020. Min Act: -0.1700
Data Index: 5897470 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4708. Min Range: -5.4708
Max Act: 5.0020. Min Act: -0.1700
Data Index: 1685445 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9708. Min Act: -0.1700
Data Index: 5833581 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9708. Min Act: -0.1700
Data Index: 6567742 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9708. Min Act: -0.1700
Data Index: 5702601 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9395. Min Act: -0.1700
Data Index: 4240109 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1338190 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1506842 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9083. Min Act: -0.1700
Data Index: 4240112 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9083. Min Act: -0.1700
Data Index: 5481382 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9083. Min Act: -0.1700
Data Index: 5690075 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4708. Min Range: -5.4708
Max Act: 4.9083. Min Act: -0.1700
Data Index: 600336 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19