Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.8889. Min Act: -0.1700
Data Index: 5134310 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.3889. Min Act: -0.1700
Data Index: 7940268 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.3889. Min Act: -0.1700
Data Index: 1621849 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.3577. Min Act: -0.1700
Data Index: 4705822 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.3264. Min Act: -0.1700
Data Index: 8086528 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.2952. Min Act: -0.1700
Data Index: 2402946 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.2639. Min Act: -0.1700
Data Index: 7701732 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.2327. Min Act: -0.1700
Data Index: 437350 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.2327. Min Act: -0.1700
Data Index: 4630176 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.2014. Min Act: -0.1700
Data Index: 7641352 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.2014. Min Act: -0.1700
Data Index: 7708730 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.2014. Min Act: -0.1700
Data Index: 3604440 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.2014. Min Act: -0.1700
Data Index: 4026929 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.1702. Min Act: -0.1700
Data Index: 8311169 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.1702. Min Act: -0.1700
Data Index: 6923609 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.1389. Min Act: -0.1700
Data Index: 8151658 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.1702. Min Act: -0.1700
Data Index: 6819881 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.1077. Min Act: -0.1700
Data Index: 5052833 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.1077. Min Act: -0.1700
Data Index: 1480975 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8889. Min Range: -6.8889
Max Act: 6.1077. Min Act: -0.1700
Data Index: 3348599 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19