Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4758 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.9591. Min Act: -0.1700
Data Index: 8783856 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.7404. Min Act: -0.1700
Data Index: 1066250 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.7404. Min Act: -0.1700
Data Index: 6041108 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.6779. Min Act: -0.1700
Data Index: 1503401 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.6779. Min Act: -0.1700
Data Index: 1530920 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.6154. Min Act: -0.1700
Data Index: 5061347 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.5841. Min Act: -0.1700
Data Index: 1265580 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.5529. Min Act: -0.1700
Data Index: 2484494 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.5841. Min Act: -0.1700
Data Index: 696864 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.5216. Min Act: -0.1700
Data Index: 1319539 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4904. Min Act: -0.1700
Data Index: 198292 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4279. Min Act: -0.1700
Data Index: 526972 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4591. Min Act: -0.1700
Data Index: 4562472 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4279. Min Act: -0.1700
Data Index: 7660140 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4279. Min Act: -0.1700
Data Index: 7049841 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4279. Min Act: -0.1700
Data Index: 3816181 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.3966. Min Act: -0.1700
Data Index: 1774995 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.3966. Min Act: -0.1700
Data Index: 470498 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.4279. Min Act: -0.1700
Data Index: 3011579 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9591. Min Range: -6.9591
Max Act: 6.3966. Min Act: -0.1700
Data Index: 2723595 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19