Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4913 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.1442. Min Act: -0.1700
Data Index: 5354067 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.1130. Min Act: -0.1700
Data Index: 3812541 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.0817. Min Act: -0.1700
Data Index: 1586682 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.0505. Min Act: -0.1700
Data Index: 5354066 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.0505. Min Act: -0.1700
Data Index: 5738100 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9880. Min Act: -0.1700
Data Index: 4145984 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9255. Min Act: -0.1700
Data Index: 7578280 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9567. Min Act: -0.1700
Data Index: 8512684 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 4481515 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 3665036 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 5290966 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 3863600 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8317. Min Act: -0.1700
Data Index: 6322174 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8317. Min Act: -0.1700
Data Index: 4972208 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8317. Min Act: -0.1700
Data Index: 487063 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8005. Min Act: -0.1700
Data Index: 7427866 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8005. Min Act: -0.1700
Data Index: 2543397 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8005. Min Act: -0.1700
Data Index: 1258427 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.7692. Min Act: -0.1700
Data Index: 5592854 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.7692. Min Act: -0.1700
Data Index: 3476083 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19