Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.6090. Min Act: -0.1700
Data Index: 7584125 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.5777. Min Act: -0.1700
Data Index: 730436 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.5465. Min Act: -0.1700
Data Index: 6128522 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.4840. Min Act: -0.1700
Data Index: 5164566 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.4527. Min Act: -0.1700
Data Index: 5134772 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.3590. Min Act: -0.1700
Data Index: 6956755 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.3590. Min Act: -0.1700
Data Index: 6149269 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.3590. Min Act: -0.1700
Data Index: 5016508 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2965. Min Act: -0.1700
Data Index: 6149266 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2965. Min Act: -0.1700
Data Index: 6244505 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2965. Min Act: -0.1700
Data Index: 4847552 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2965. Min Act: -0.1700
Data Index: 8229261 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2652. Min Act: -0.1700
Data Index: 1811610 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2340. Min Act: -0.1700
Data Index: 6250894 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2340. Min Act: -0.1700
Data Index: 8111024 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2027. Min Act: -0.1700
Data Index: 7083117 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2027. Min Act: -0.1700
Data Index: 733387 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2027. Min Act: -0.1700
Data Index: 7306119 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.1715. Min Act: -0.1700
Data Index: 6819040 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.1402. Min Act: -0.1700
Data Index: 2847313 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19