Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.3142. Min Act: -0.1700
Data Index: 2091227 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1892. Min Act: -0.1700
Data Index: 2821895 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1892. Min Act: -0.1700
Data Index: 4486475 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1579. Min Act: -0.1700
Data Index: 7428900 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1267. Min Act: -0.1700
Data Index: 2628370 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0954. Min Act: -0.1700
Data Index: 3522340 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0954. Min Act: -0.1700
Data Index: 239146 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0642. Min Act: -0.1700
Data Index: 2144457 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0642. Min Act: -0.1700
Data Index: 4665920 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0329. Min Act: -0.1700
Data Index: 1883100 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0642. Min Act: -0.1700
Data Index: 4370258 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0642. Min Act: -0.1700
Data Index: 4352923 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0642. Min Act: -0.1700
Data Index: 8015334 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0642. Min Act: -0.1700
Data Index: 1693058 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0329. Min Act: -0.1700
Data Index: 832555 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0642. Min Act: -0.1700
Data Index: 4332890 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0642. Min Act: -0.1700
Data Index: 5910094 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0329. Min Act: -0.1700
Data Index: 8139890 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0329. Min Act: -0.1700
Data Index: 5811927 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.0016. Min Act: -0.1700
Data Index: 5255301 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19