Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1495 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.4455. Min Act: -0.1700
Data Index: 7086919 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.4142. Min Act: -0.1700
Data Index: 1144690 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2580. Min Act: -0.1700
Data Index: 5492942 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2580. Min Act: -0.1700
Data Index: 5820866 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2580. Min Act: -0.1700
Data Index: 8779917 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2267. Min Act: -0.1700
Data Index: 1723103 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2267. Min Act: -0.1700
Data Index: 7230902 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2580. Min Act: -0.1700
Data Index: 45072 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1955. Min Act: -0.1700
Data Index: 1002413 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1955. Min Act: -0.1700
Data Index: 1022017 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1955. Min Act: -0.1700
Data Index: 7019238 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1642. Min Act: -0.1700
Data Index: 34793 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1642. Min Act: -0.1700
Data Index: 847897 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1642. Min Act: -0.1700
Data Index: 112876 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1642. Min Act: -0.1699
Data Index: 7600494 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1642. Min Act: -0.1700
Data Index: 2057501 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1955. Min Act: -0.1700
Data Index: 7560508 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1642. Min Act: -0.1700
Data Index: 5641193 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1330. Min Act: -0.1700
Data Index: 6547162 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1330. Min Act: -0.1700
Data Index: 6651457 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19