Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4877 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0890. Min Range: -7.0890
Max Act: 7.0890. Min Act: -0.1700
Data Index: 3111321 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.7453. Min Act: -0.1700
Data Index: 4406066 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.7140. Min Act: -0.1700
Data Index: 5063980 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.7140. Min Act: -0.1700
Data Index: 948868 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.6828. Min Act: -0.1700
Data Index: 6034878 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.6515. Min Act: -0.1700
Data Index: 3860560 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5890. Min Act: -0.1700
Data Index: 7559821 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.6203. Min Act: -0.1700
Data Index: 4332840 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.6203. Min Act: -0.1700
Data Index: 8648128 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5578. Min Act: -0.1700
Data Index: 6738866 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5578. Min Act: -0.1700
Data Index: 5993102 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5265. Min Act: -0.1700
Data Index: 264160 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5265. Min Act: -0.1700
Data Index: 3548847 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5265. Min Act: -0.1700
Data Index: 4310176 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5265. Min Act: -0.1700
Data Index: 6237721 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5265. Min Act: -0.1700
Data Index: 163239 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5265. Min Act: -0.1700
Data Index: 1225776 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.4640. Min Act: -0.1700
Data Index: 6611519 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.4953. Min Act: -0.1700
Data Index: 5906483 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0890. Min Range: -7.0890
Max Act: 6.5265. Min Act: -0.1700
Data Index: 6821930 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19