Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2133 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2371. Min Range: -6.2371
Max Act: 6.2371. Min Act: -0.1700
Data Index: 7030970 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2371. Min Range: -6.2371
Max Act: 6.0184. Min Act: -0.1700
Data Index: 2176405 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.9559. Min Act: -0.1700
Data Index: 2664631 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.8934. Min Act: -0.1700
Data Index: 6108990 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.8621. Min Act: -0.1700
Data Index: 846788 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.8309. Min Act: -0.1700
Data Index: 67610 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.8309. Min Act: -0.1700
Data Index: 142143 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.7684. Min Act: -0.1700
Data Index: 3027751 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.7684. Min Act: -0.1700
Data Index: 7507127 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.7371. Min Act: -0.1700
Data Index: 1530655 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.7059. Min Act: -0.1700
Data Index: 899268 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.6746. Min Act: -0.1700
Data Index: 5386767 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.7059. Min Act: -0.1700
Data Index: 3418134 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.6746. Min Act: -0.1700
Data Index: 6978736 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.6746. Min Act: -0.1700
Data Index: 5528788 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.6434. Min Act: -0.1700
Data Index: 6384117 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.6121. Min Act: -0.1700
Data Index: 5824243 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.6121. Min Act: -0.1700
Data Index: 2855243 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.6121. Min Act: -0.1700
Data Index: 2636198 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2371. Min Range: -6.2371
Max Act: 5.6434. Min Act: -0.1700
Data Index: 6513928 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19