Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2532 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.2142. Min Act: -0.1700
Data Index: 4695464 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.1829. Min Act: -0.1700
Data Index: 4085713 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0892. Min Act: -0.1700
Data Index: 8062989 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0892. Min Act: -0.1700
Data Index: 8808373 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0892. Min Act: -0.1700
Data Index: 7558288 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0579. Min Act: -0.1700
Data Index: 8673015 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0579. Min Act: -0.1700
Data Index: 8055213 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0267. Min Act: -0.1700
Data Index: 5714862 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0267. Min Act: -0.1700
Data Index: 4666980 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 4807668 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 7148904 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 5792086 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 6307160 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 616090 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9329. Min Act: -0.1700
Data Index: 8457042 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9017. Min Act: -0.1700
Data Index: 5726379 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9017. Min Act: -0.1700
Data Index: 6900839 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9329. Min Act: -0.1700
Data Index: 7259923 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9329. Min Act: -0.1700
Data Index: 4419691 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9017. Min Act: -0.1700
Data Index: 6101716 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19