Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 631 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1404. Min Range: -4.1404
Max Act: 4.1404. Min Act: -0.1700
Data Index: 6212783 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.9529. Min Act: -0.1700
Data Index: 7134581 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.9216. Min Act: -0.1700
Data Index: 7134582 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.8591. Min Act: -0.1700
Data Index: 3475172 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.8591. Min Act: -0.1700
Data Index: 2322548 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.8278. Min Act: -0.1700
Data Index: 3915676 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.8591. Min Act: -0.1700
Data Index: 8785449 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.8591. Min Act: -0.1700
Data Index: 1543864 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.8278. Min Act: -0.1700
Data Index: 1793841 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.8278. Min Act: -0.1700
Data Index: 1228409 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.8591. Min Act: -0.1700
Data Index: 6607191 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7965. Min Act: -0.1700
Data Index: 1838793 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7965. Min Act: -0.1700
Data Index: 3211606 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7965. Min Act: -0.1700
Data Index: 2808861 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7653. Min Act: -0.1700
Data Index: 7221186 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7653. Min Act: -0.1700
Data Index: 3475164 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7340. Min Act: -0.1700
Data Index: 5911341 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7027. Min Act: -0.1700
Data Index: 4288366 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.6714. Min Act: -0.1700
Data Index: 2594378 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1404. Min Range: -4.1404
Max Act: 3.7027. Min Act: -0.1700
Data Index: 783126 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19