Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.5834. Min Act: -0.1700
Data Index: 7623063 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.2084. Min Act: -0.1700
Data Index: 782093 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.2084. Min Act: -0.1700
Data Index: 4845454 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0834. Min Act: -0.1700
Data Index: 7691724 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0834. Min Act: -0.1700
Data Index: 957809 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0521. Min Act: -0.1700
Data Index: 6071135 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0521. Min Act: -0.1700
Data Index: 5914091 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0521. Min Act: -0.1700
Data Index: 1896900 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0209. Min Act: -0.1700
Data Index: 2153116 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0209. Min Act: -0.1700
Data Index: 3720997 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0521. Min Act: -0.1700
Data Index: 226493 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5834. Min Range: -5.5834
Max Act: 5.0209. Min Act: -0.1700
Data Index: 6906413 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9896. Min Act: -0.1700
Data Index: 645764 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9584. Min Act: -0.1700
Data Index: 4490632 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9271. Min Act: -0.1700
Data Index: 4677406 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9271. Min Act: -0.1700
Data Index: 8120014 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9271. Min Act: -0.1700
Data Index: 6657379 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9271. Min Act: -0.1700
Data Index: 8760214 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9271. Min Act: -0.1700
Data Index: 319696 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5834. Min Range: -5.5834
Max Act: 4.9271. Min Act: -0.1700
Data Index: 1506890 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19