Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.7046. Min Act: -0.1700
Data Index: 5230702 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.6421. Min Act: -0.1700
Data Index: 1546608 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.5796. Min Act: -0.1700
Data Index: 506648 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.5171. Min Act: -0.1700
Data Index: 5048301 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.5171. Min Act: -0.1700
Data Index: 506643 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.4859. Min Act: -0.1700
Data Index: 506638 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.4859. Min Act: -0.1700
Data Index: 506647 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.4546. Min Act: -0.1700
Data Index: 438004 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.4234. Min Act: -0.1700
Data Index: 5427420 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.4234. Min Act: -0.1700
Data Index: 3648095 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.4234. Min Act: -0.1700
Data Index: 4008100 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3921. Min Act: -0.1700
Data Index: 1059103 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3921. Min Act: -0.1700
Data Index: 506639 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3609. Min Act: -0.1700
Data Index: 478508 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3609. Min Act: -0.1700
Data Index: 3412588 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3609. Min Act: -0.1700
Data Index: 4567941 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3609. Min Act: -0.1700
Data Index: 506636 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3609. Min Act: -0.1700
Data Index: 1879209 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3609. Min Act: -0.1700
Data Index: 506645 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7046. Min Range: -5.7046
Max Act: 5.3609. Min Act: -0.1700
Data Index: 1009949 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19