Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1659 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5534. Min Range: -6.5534
Max Act: 6.5534. Min Act: -0.1700
Data Index: 3025266 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5534. Min Range: -6.5534
Max Act: 6.4284. Min Act: -0.1700
Data Index: 1124899 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5534. Min Range: -6.5534
Max Act: 6.0534. Min Act: -0.1700
Data Index: 5016699 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.9284. Min Act: -0.1700
Data Index: 8634648 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.8346. Min Act: -0.1700
Data Index: 2290869 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.8034. Min Act: -0.1700
Data Index: 8129925 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.8034. Min Act: -0.1700
Data Index: 1013343 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7721. Min Act: -0.1700
Data Index: 6081538 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7721. Min Act: -0.1700
Data Index: 4052319 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7409. Min Act: -0.1700
Data Index: 7348076 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7409. Min Act: -0.1700
Data Index: 4803984 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7409. Min Act: -0.1700
Data Index: 458478 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7096. Min Act: -0.1700
Data Index: 5910487 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7409. Min Act: -0.1700
Data Index: 2006572 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7096. Min Act: -0.1700
Data Index: 387833 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7096. Min Act: -0.1700
Data Index: 1585281 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.7096. Min Act: -0.1700
Data Index: 3654019 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.6784. Min Act: -0.1700
Data Index: 2259337 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.6471. Min Act: -0.1700
Data Index: 8641241 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5534. Min Range: -6.5534
Max Act: 5.6159. Min Act: -0.1700
Data Index: 1662268 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19