Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2222 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3455. Min Range: -5.3455
Max Act: 5.3455. Min Act: -0.1700
Data Index: 3403287 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3455. Min Range: -5.3455
Max Act: 5.1892. Min Act: -0.1700
Data Index: 6605861 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3455. Min Range: -5.3455
Max Act: 5.0642. Min Act: -0.1700
Data Index: 8640082 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3455. Min Range: -5.3455
Max Act: 5.0330. Min Act: -0.1700
Data Index: 1844509 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3455. Min Range: -5.3455
Max Act: 5.0330. Min Act: -0.1700
Data Index: 2052136 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3455. Min Range: -5.3455
Max Act: 5.0017. Min Act: -0.1700
Data Index: 4195024 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.9705. Min Act: -0.1700
Data Index: 2421765 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.9705. Min Act: -0.1700
Data Index: 5149936 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.9392. Min Act: -0.1700
Data Index: 5159638 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.9080. Min Act: -0.1700
Data Index: 667685 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.9080. Min Act: -0.1700
Data Index: 2499494 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8767. Min Act: -0.1700
Data Index: 2565366 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8767. Min Act: -0.1700
Data Index: 8495117 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6057536 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8767. Min Act: -0.1700
Data Index: 7663304 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6573087 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8767. Min Act: -0.1700
Data Index: 2695791 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6105611 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6085433 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3455. Min Range: -5.3455
Max Act: 4.8455. Min Act: -0.1700
Data Index: 3304104 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19