Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.8185. Min Act: -0.1700
Data Index: 3149031 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.3810. Min Act: -0.1700
Data Index: 6270652 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.2248. Min Act: -0.1700
Data Index: 3041276 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.1935. Min Act: -0.1700
Data Index: 674769 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.1935. Min Act: -0.1700
Data Index: 7773957 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.1623. Min Act: -0.1700
Data Index: 2167616 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.1623. Min Act: -0.1700
Data Index: 5171398 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 6050695 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 3724885 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0998. Min Act: -0.1700
Data Index: 443557 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0998. Min Act: -0.1700
Data Index: 5879981 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0998. Min Act: -0.1700
Data Index: 7120569 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0998. Min Act: -0.1700
Data Index: 4038839 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 6822036 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0685. Min Act: -0.1700
Data Index: 8764839 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0685. Min Act: -0.1700
Data Index: 2348878 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0373. Min Act: -0.1700
Data Index: 7086570 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0060. Min Act: -0.1700
Data Index: 4732157 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0060. Min Act: -0.1700
Data Index: 2799296 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8185. Min Range: -5.8185
Max Act: 5.0060. Min Act: -0.1700
Data Index: 7651371 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19