Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.5014. Min Act: -0.1700
Data Index: 1461867 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.3451. Min Act: -0.1700
Data Index: 5306773 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.2514. Min Act: -0.1700
Data Index: 7947376 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1889. Min Act: -0.1700
Data Index: 8200317 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1889. Min Act: -0.1700
Data Index: 1939790 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1576. Min Act: -0.1700
Data Index: 1617179 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1576. Min Act: -0.1700
Data Index: 4596523 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 7819133 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 1235535 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0951. Min Act: -0.1700
Data Index: 2996524 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 6753592 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 2348645 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 8021233 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0951. Min Act: -0.1700
Data Index: 2987845 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0639. Min Act: -0.1700
Data Index: 5631553 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0951. Min Act: -0.1700
Data Index: 1582225 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0639. Min Act: -0.1700
Data Index: 3308865 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0639. Min Act: -0.1700
Data Index: 11323 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0639. Min Act: -0.1700
Data Index: 8276804 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0326. Min Act: -0.1699
Data Index: 2972631 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19