Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5707 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.6903. Min Act: -0.1700
Data Index: 8484734 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.6591. Min Act: -0.1700
Data Index: 5870337 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.6591. Min Act: -0.1700
Data Index: 3824202 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.6278. Min Act: -0.1700
Data Index: 4771001 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.5653. Min Act: -0.1700
Data Index: 4154228 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.5341. Min Act: -0.1700
Data Index: 8668539 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.5653. Min Act: -0.1700
Data Index: 3418879 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.5341. Min Act: -0.1700
Data Index: 5557519 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.5653. Min Act: -0.1700
Data Index: 1888035 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.5653. Min Act: -0.1700
Data Index: 3889249 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.4716. Min Act: -0.1700
Data Index: 4816969 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.4403. Min Act: -0.1700
Data Index: 1160603 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.4716. Min Act: -0.1700
Data Index: 5651991 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.4091. Min Act: -0.1700
Data Index: 931544 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.4403. Min Act: -0.1700
Data Index: 5687832 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.4403. Min Act: -0.1700
Data Index: 4359200 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.4091. Min Act: -0.1700
Data Index: 1584968 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.3778. Min Act: -0.1700
Data Index: 8586146 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.3778. Min Act: -0.1700
Data Index: 773472 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6903. Min Range: -7.6903
Max Act: 7.3466. Min Act: -0.1700
Data Index: 2060967 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19