Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4018 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1756. Min Range: -4.1756
Max Act: 4.1756. Min Act: -0.1700
Data Index: 5100220 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.8004. Min Act: -0.1700
Data Index: 3707357 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.7692. Min Act: -0.1700
Data Index: 7244147 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.7222. Min Act: -0.1700
Data Index: 445460 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.7066. Min Act: -0.1700
Data Index: 2411788 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.6753. Min Act: -0.1700
Data Index: 1598538 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.6597. Min Act: -0.1700
Data Index: 720097 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.6753. Min Act: -0.1700
Data Index: 3719038 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.6753. Min Act: -0.1700
Data Index: 5550878 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.6597. Min Act: -0.1700
Data Index: 4718455 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.6597. Min Act: -0.1700
Data Index: 1969336 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.6127. Min Act: -0.1700
Data Index: 833066 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.5971. Min Act: -0.1700
Data Index: 8301206 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.5971. Min Act: -0.1700
Data Index: 3602665 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.5971. Min Act: -0.1700
Data Index: 179996 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.5814. Min Act: -0.1700
Data Index: 2190600 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.5971. Min Act: -0.1700
Data Index: 5571537 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.5658. Min Act: -0.1700
Data Index: 547550 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.5658. Min Act: -0.1700
Data Index: 6071940 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1756. Min Range: -4.1756
Max Act: 3.5658. Min Act: -0.1700
Data Index: 709108 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19