Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1563 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.6396. Min Act: -0.1700
Data Index: 682460 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.5146. Min Act: -0.1700
Data Index: 2044932 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.5146. Min Act: -0.1700
Data Index: 3481372 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.4521. Min Act: -0.1700
Data Index: 5928263 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.4521. Min Act: -0.1700
Data Index: 8226376 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.4521. Min Act: -0.1700
Data Index: 4881306 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.3896. Min Act: -0.1700
Data Index: 8331422 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.3896. Min Act: -0.1700
Data Index: 7487851 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.4521. Min Act: -0.1700
Data Index: 4779846 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.3271. Min Act: -0.1700
Data Index: 3603159 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.3271. Min Act: -0.1700
Data Index: 8182554 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.2646. Min Act: -0.1700
Data Index: 1866000 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.2646. Min Act: -0.1700
Data Index: 1808637 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.2646. Min Act: -0.1700
Data Index: 7729895 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.2646. Min Act: -0.1700
Data Index: 4606590 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.2646. Min Act: -0.1700
Data Index: 7506600 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.2021. Min Act: -0.1700
Data Index: 6988567 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.3271. Min Act: -0.1700
Data Index: 2720586 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.2646. Min Act: -0.1700
Data Index: 955574 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.6396. Min Range: -14.6396
Max Act: 14.2021. Min Act: -0.1700
Data Index: 5801375 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19