Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5550 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1828. Min Range: -3.1828
Max Act: 3.1828. Min Act: -0.1700
Data Index: 6819442 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9936. Min Act: -0.1700
Data Index: 381834 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9936. Min Act: -0.1700
Data Index: 6119941 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9778. Min Act: -0.1700
Data Index: 942017 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9778. Min Act: -0.1700
Data Index: 290718 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9462. Min Act: -0.1700
Data Index: 1907386 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9620. Min Act: -0.1700
Data Index: 4674446 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9462. Min Act: -0.1700
Data Index: 5982656 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9462. Min Act: -0.1700
Data Index: 167193 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9462. Min Act: -0.1700
Data Index: 2569767 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9303. Min Act: -0.1700
Data Index: 6381174 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9462. Min Act: -0.1700
Data Index: 2472208 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9462. Min Act: -0.1700
Data Index: 848704 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9303. Min Act: -0.1700
Data Index: 4038173 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9303. Min Act: -0.1700
Data Index: 4420440 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9145. Min Act: -0.1700
Data Index: 4242894 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9145. Min Act: -0.1700
Data Index: 1278133 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9145. Min Act: -0.1700
Data Index: 6078695 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9145. Min Act: -0.1700
Data Index: 3926260 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1828. Min Range: -3.1828
Max Act: 2.9145. Min Act: -0.1700
Data Index: 2761810 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19