Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6046 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5643. Min Act: -0.1700
Data Index: 1900052 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5018. Min Act: -0.1700
Data Index: 8510270 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 1338487 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 2386342 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4081. Min Act: -0.1700
Data Index: 1338489 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4081. Min Act: -0.1700
Data Index: 3356667 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.3768. Min Act: -0.1700
Data Index: 3356669 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.3768. Min Act: -0.1700
Data Index: 4022738 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.3456. Min Act: -0.1700
Data Index: 1242062 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.3456. Min Act: -0.1700
Data Index: 831330 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.3456. Min Act: -0.1700
Data Index: 3456857 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.3143. Min Act: -0.1700
Data Index: 6683450 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.2831. Min Act: -0.1700
Data Index: 174974 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.3143. Min Act: -0.1700
Data Index: 3356671 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.3143. Min Act: -0.1700
Data Index: 831326 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.2831. Min Act: -0.1700
Data Index: 4192727 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.2518. Min Act: -0.1700
Data Index: 372134 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.2831. Min Act: -0.1700
Data Index: 4952008 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.2831. Min Act: -0.1700
Data Index: 5036120 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.2831. Min Act: -0.1700
Data Index: 5396768 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19