Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1546 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3104. Min Range: -7.3104
Max Act: 7.3104. Min Act: -0.1700
Data Index: 3410329 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3104. Min Range: -7.3104
Max Act: 7.2479. Min Act: -0.1700
Data Index: 7956031 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3104. Min Range: -7.3104
Max Act: 7.1229. Min Act: -0.1700
Data Index: 6684556 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3104. Min Range: -7.3104
Max Act: 7.0604. Min Act: -0.1700
Data Index: 3876054 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3104. Min Range: -7.3104
Max Act: 7.0291. Min Act: -0.1700
Data Index: 120915 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3104. Min Range: -7.3104
Max Act: 7.0291. Min Act: -0.1700
Data Index: 5199426 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.8416. Min Act: -0.1700
Data Index: 13245 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7791. Min Act: -0.1700
Data Index: 555554 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.8104. Min Act: -0.1700
Data Index: 4615083 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.8416. Min Act: -0.1700
Data Index: 2108323 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.8104. Min Act: -0.1700
Data Index: 5178083 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7791. Min Act: -0.1700
Data Index: 709264 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7791. Min Act: -0.1700
Data Index: 2873658 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7791. Min Act: -0.1700
Data Index: 704068 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7479. Min Act: -0.1700
Data Index: 4878569 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7479. Min Act: -0.1700
Data Index: 6709336 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7791. Min Act: -0.1700
Data Index: 8275450 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7479. Min Act: -0.1700
Data Index: 5813363 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7166. Min Act: -0.1700
Data Index: 8062295 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3104. Min Range: -7.3104
Max Act: 6.7166. Min Act: -0.1700
Data Index: 2305075 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19