Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.6063. Min Act: -0.1700
Data Index: 5838441 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.6063. Min Act: -0.1700
Data Index: 3498235 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.5751. Min Act: -0.1700
Data Index: 1090098 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.5751. Min Act: -0.1700
Data Index: 8022620 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.6063. Min Act: -0.1700
Data Index: 4899034 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.6376. Min Act: -0.1700
Data Index: 1203743 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.5126. Min Act: -0.1700
Data Index: 6749019 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.5126. Min Act: -0.1700
Data Index: 2502207 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.5126. Min Act: -0.1700
Data Index: 827492 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.4813. Min Act: -0.1700
Data Index: 4005066 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.4813. Min Act: -0.1700
Data Index: 5261927 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.4501. Min Act: -0.1700
Data Index: 4436776 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.4501. Min Act: -0.1700
Data Index: 6858656 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.3876. Min Act: -0.1700
Data Index: 6685700 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.3876. Min Act: -0.1700
Data Index: 8149699 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.3876. Min Act: -0.1700
Data Index: 8014506 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.3876. Min Act: -0.1700
Data Index: 7324420 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.3876. Min Act: -0.1700
Data Index: 4690869 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.3563. Min Act: -0.1700
Data Index: 4552666 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6376. Min Range: -7.6376
Max Act: 7.3251. Min Act: -0.1700
Data Index: 6146318 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19