Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7563. Min Act: -0.1699
Data Index: 3340451 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7391. Min Act: -0.1700
Data Index: 5434604 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7391. Min Act: -0.1700
Data Index: 7872754 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7131. Min Act: -0.1700
Data Index: 918321 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7131. Min Act: -0.1700
Data Index: 6352674 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7218. Min Act: -0.1700
Data Index: 3871439 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7131. Min Act: -0.1700
Data Index: 5990708 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7218. Min Act: -0.1700
Data Index: 897757 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7218. Min Act: -0.1700
Data Index: 1044615 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7218. Min Act: -0.1700
Data Index: 4664770 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.7131. Min Act: -0.1700
Data Index: 2713117 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6958. Min Act: -0.1700
Data Index: 4799157 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6784. Min Act: -0.1698
Data Index: 118981 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6871. Min Act: -0.1700
Data Index: 2460558 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6958. Min Act: -0.1700
Data Index: 2972690 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6871. Min Act: -0.1700
Data Index: 1231250 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6697. Min Act: -0.1700
Data Index: 2862250 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6697. Min Act: -0.1700
Data Index: 5479335 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6610. Min Act: -0.1700
Data Index: 1576703 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7563. Min Range: -1.7563
Max Act: 1.6697. Min Act: -0.1700
Data Index: 6158271 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19