Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1186 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.7642. Min Act: -0.1700
Data Index: 6902807 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.5767. Min Act: -0.1700
Data Index: 6030201 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.5767. Min Act: -0.1700
Data Index: 1006715 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.4517. Min Act: -0.1700
Data Index: 449500 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.4517. Min Act: -0.1700
Data Index: 674396 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3892. Min Act: -0.1700
Data Index: 7300662 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3892. Min Act: -0.1700
Data Index: 848532 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3892. Min Act: -0.1700
Data Index: 6429744 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3892. Min Act: -0.1700
Data Index: 4896977 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 5843065 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 5853593 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3892. Min Act: -0.1700
Data Index: 7257867 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 1417981 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 6057450 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 7333217 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 4306301 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 8398079 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 1125369 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.3267. Min Act: -0.1700
Data Index: 8492809 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7642. Min Range: -7.7642
Max Act: 7.2642. Min Act: -0.1700
Data Index: 6302486 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19