Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.7304. Min Act: -0.1700
Data Index: 8326641 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.6679. Min Act: -0.1700
Data Index: 2413583 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.6054. Min Act: -0.1700
Data Index: 4858180 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.6367. Min Act: -0.1700
Data Index: 4611931 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.6367. Min Act: -0.1700
Data Index: 442191 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.6367. Min Act: -0.1700
Data Index: 5410150 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.6367. Min Act: -0.1700
Data Index: 4636659 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.6054. Min Act: -0.1700
Data Index: 7342383 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 5671123 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.6054. Min Act: -0.1700
Data Index: 5045803 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 4903106 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 5302738 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 7340742 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 5151310 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 7397073 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 947794 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5429. Min Act: -0.1700
Data Index: 8255813 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 2945983 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 3921938 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7304. Min Range: -4.7304
Max Act: 4.5742. Min Act: -0.1700
Data Index: 2497725 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19