Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.3654. Min Act: -0.1700
Data Index: 5298222 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.3654. Min Act: -0.1700
Data Index: 7173679 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.3341. Min Act: -0.1700
Data Index: 2206665 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.3341. Min Act: -0.1700
Data Index: 1864124 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.3029. Min Act: -0.1700
Data Index: 1166082 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.3029. Min Act: -0.1700
Data Index: 2050432 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.2716. Min Act: -0.1700
Data Index: 4601398 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.2716. Min Act: -0.1700
Data Index: 2468112 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.2716. Min Act: -0.1700
Data Index: 7994736 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.2404. Min Act: -0.1700
Data Index: 4075179 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.2404. Min Act: -0.1700
Data Index: 532727 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.2091. Min Act: -0.1700
Data Index: 2582393 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.2404. Min Act: -0.1700
Data Index: 6851749 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.1779. Min Act: -0.1700
Data Index: 2619897 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.1466. Min Act: -0.1700
Data Index: 2963141 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.1779. Min Act: -0.1700
Data Index: 5218868 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.1779. Min Act: -0.1700
Data Index: 1028904 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.1466. Min Act: -0.1700
Data Index: 8097626 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.1466. Min Act: -0.1700
Data Index: 5814420 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3654. Min Range: -5.3654
Max Act: 5.1466. Min Act: -0.1700
Data Index: 6784648 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19