Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0591. Min Range: -6.0591
Max Act: 6.0591. Min Act: -0.1700
Data Index: 8241596 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0591. Min Range: -6.0591
Max Act: 6.0279. Min Act: -0.1700
Data Index: 4317893 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.9654. Min Act: -0.1700
Data Index: 16883 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.9654. Min Act: -0.1700
Data Index: 8060264 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.9654. Min Act: -0.1700
Data Index: 933061 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.9029. Min Act: -0.1700
Data Index: 8060262 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.8716. Min Act: -0.1700
Data Index: 856544 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.8091. Min Act: -0.1700
Data Index: 1652276 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.8091. Min Act: -0.1700
Data Index: 856546 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.8091. Min Act: -0.1700
Data Index: 4317892 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.7779. Min Act: -0.1700
Data Index: 2698745 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.7466. Min Act: -0.1700
Data Index: 1326509 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.7466. Min Act: -0.1700
Data Index: 2292989 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.7154. Min Act: -0.1700
Data Index: 6079425 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.7154. Min Act: -0.1700
Data Index: 4266588 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.6529. Min Act: -0.1700
Data Index: 8062585 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.6529. Min Act: -0.1700
Data Index: 6155201 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.6529. Min Act: -0.1700
Data Index: 1652272 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.6216. Min Act: -0.1700
Data Index: 6081277 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0591. Min Range: -6.0591
Max Act: 5.6216. Min Act: -0.1700
Data Index: 4651660 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19